with tf.function

/Users/ikkamens/open_source/PILCO/venv/bin/python /Users/ikkamens/open_source/PILCO/examples/safe_cars_run.py
Action: [-0.16857667]
State : [-5.44107607 0.92721038 -4.43702446 1.0672268 ]
Return so far: -1
Action: [-0.2517018]
State : [-4.97747088 0.80089587 -3.90341106 1.0672268 ]
Return so far: -2
Action: [0.08794767]
State : [-4.57702295 0.84446926 -3.36979767 1.0672268 ]
Return so far: -3
Action: [0.25404316]
State : [-4.15478832 0.97106861 -2.83618427 1.0672268 ]
Return so far: -4
Action: [-0.09211302]
State : [-3.66925401 0.92452656 -2.30257087 1.0672268 ]
Return so far: -5
Action: [0.22967832]
State : [-3.20699073 1.03890346 -1.76895747 1.0672268 ]
Return so far: -6
Action: [0.08557069]
State : [-2.687539 1.08116935 -1.23534407 1.0672268 ]
Return so far: -7
Action: [0.29930145]
State : [-2.14695433 1.23027949 -0.70173068 1.0672268 ]
Return so far: -8
Action: [0.11899719]
State : [-1.53181458 1.28916295 -0.16811728 1.0672268 ]
Return so far: -9
Action: [0.07483634]
State : [-0.8872331 1.32593654 0.36549612 1.0672268 ]
Return so far: -10
Action: [-0.35986045]
State : [-0.22426483 1.14534335 0.89910952 1.0672268 ]
Return so far: -11
Action: [-0.13109754]
State : [0.34840684 1.0792219 1.43272292 1.0672268 ]
Return so far: -10
Action: [0.35907292]
State : [0.88801779 1.25821876 1.96633631 1.0672268 ]
Return so far: -9
Action: [-0.13456364]
State : [1.51712717 1.19030783 2.49994971 1.0672268 ]
Return so far: -8
Action: [-0.17173328]
State : [2.11228108 1.10384603 3.03356311 1.0672268 ]
Return so far: -7
Action: [-0.35090148]
State : [2.6642041 0.92784337 3.56717651 1.0672268 ]
Return so far: -6
Action: [-0.23300388]
State : [3.12812578 0.81087751 4.10078991 1.0672268 ]
Return so far: -5
Action: [-0.15200664]
State : [3.53356454 0.73446875 4.6344033 1.0672268 ]
Return so far: -4
Action: [-0.22756428]
State : [3.90079891 0.62031937 5.1680167 1.0672268 ]
Return so far: -3
Action: [-0.29081076]
State : [4.2109586 0.47460383 5.7016301 1.0672268 ]
Return so far: -2
Action: [-0.38611293]
State : [4.44826051 0.28131007 6.2352435 1.0672268 ]
Return so far: -1
Action: [0.10783496]
State : [4.58891554 0.33508689 6.7688569 1.0672268 ]
Return so far: 0
Action: [0.3915995]
State : [4.75645899 0.5307191 7.30247029 1.0672268 ]
Return so far: 1
Action: [-0.14201239]
State : [5.02181854 0.45944755 7.83608369 1.0672268 ]
Return so far: 2
Action: [0.28035915]
State : [5.25154232 0.5993974 8.36969709 1.0672268 ]
Return so far: 3
Action: [-0.05426499]
State : [-5.45863243 0.94306383 -4.47376771 0.99545928]
Return so far: -1
Action: [-0.05110177]
State : [-4.98710051 0.91704141 -3.97603806 0.99545928]
Return so far: -2
Action: [0.0091927]
State : [-4.52857981 0.92117924 -3.47830842 0.99545928]
Return so far: -3
Action: [0.09821718]
State : [-4.06799019 0.96982724 -2.98057878 0.99545928]
Return so far: -4
Action: [0.07218124]
State : [-3.58307657 1.00543295 -2.48284914 0.99545928]
Return so far: -5
Action: [-0.39567742]
State : [-3.0803601 0.80709152 -1.9851195 0.99545928]
Return so far: -6
Action: [0.21079117]
State : [-2.67681433 0.91208356 -1.48738985 0.99545928]
Return so far: -7
Action: [-0.0166761]
State : [-2.22077255 0.90328947 -0.98966021 0.99545928]
Return so far: -8
Action: [0.22222225]
State : [-1.76912782 1.01394895 -0.49193057 0.99545928]
Return so far: -9
Action: [0.1483339]
State : [-1.26215334 1.08760893 0.00579907 0.99545928]
Return so far: -10
Action: [0.34490374]
State : [-0.71834888 1.25951699 0.50352871 0.99545928]
Return so far: -11
Action: [0.03959491]
State : [-0.08859038 1.27868469 1.00125836 0.99545928]
Return so far: -12
Action: [0.0309477]
State : [0.55075197 1.2935192 1.498988 0.99545928]
Return so far: -11
Action: [0.04701564]
State : [1.19751157 1.31638026 1.99671764 0.99545928]
Return so far: -10
Action: [0.01067787]
State : [1.8557017 1.32106101 2.49444728 0.99545928]
Return so far: -9
Action: [-0.1401066]
State : [2.5162322 1.25034717 2.99217692 0.99545928]
Return so far: -8
Action: [0.18481174]
State : [3.14140579 1.34212787 3.48990656 0.99545928]
Return so far: -7
Action: [-0.09629767]
State : [3.81246972 1.29330797 3.98763621 0.99545928]
Return so far: -6
Action: [0.03307438]
State : [4.45912371 1.30919851 4.48536585 0.99545928]
Return so far: -5
Action: [-0.01275122]
State : [5.11372296 1.3021683 4.98309549 0.99545928]
Return so far: -4
Action: [-0.22173822]
State : [5.76480711 1.1906481 5.48082513 0.99545928]
Return so far: -3
Action: [0.32866764]
State : [6.36013116 1.3543866 5.97855477 0.99545928]
Return so far: -2
Action: [0.30818483]
State : [7.03732446 1.50780182 6.47628442 0.99545928]
Return so far: -1
Action: [-0.19360727]
State : [7.79122538 1.41024429 6.97401406 0.99545928]
Return so far: 0
Action: [-0.3904737]
State : [8.49634752 1.21430232 7.4717437 0.99545928]
Return so far: 1
Action: [0.2845467]
State : [-5.49693759 1.15408515 -4.47386459 1.04362821]
Return so far: -1
Action: [-0.08626179]
State : [-4.91989501 1.11037721 -3.95205049 1.04362821]
Return so far: -2
Action: [-0.2573699]
State : [-4.36470641 0.98113707 -3.43023639 1.04362821]
Return so far: -3
Action: [-0.20044151]
State : [-3.87413788 0.88042574 -2.90842228 1.04362821]
Return so far: -4
Action: [0.17264749]
State : [-3.43392501 0.96630928 -2.38660818 1.04362821]
Return so far: -5
Action: [0.21322605]
State : [-2.95077037 1.07243915 -1.86479408 1.04362821]
Return so far: -6
Action: [-0.33022222]
State : [-2.41455079 0.90679182 -1.34297997 1.04362821]
Return so far: -7
Action: [0.09473589]
State : [-1.96115489 0.95370637 -0.82116587 1.04362821]
Return so far: -8
Action: [-0.2691211]
State : [-1.4843017 0.81866896 -0.29935177 1.04362821]
Return so far: -9
Action: [-0.25992203]
State : [-1.07496722 0.68829861 0.22246233 1.04362821]
Return so far: -10
Action: [-0.26452294]
State : [-0.73081792 0.55569299 0.74427644 1.04362821]
Return so far: -11
Action: [0.3609785]
State : [-0.45297142 0.7359044 1.26609054 1.04362821]
Return so far: -12
Action: [-0.29991847]
State : [-0.08501922 0.58557721 1.78790464 1.04362821]
Return so far: -13
Action: [-0.37121972]
State : [0.20776938 0.39967456 2.30971874 1.04362821]
Return so far: -12
Action: [0.21602757]
State : [0.40760667 0.50748851 2.83153285 1.04362821]
Return so far: -11
Action: [0.15480466]
State : [0.66135092 0.5846371 3.35334695 1.04362821]
Return so far: -10
Action: [0.32753915]
State : [0.95366947 0.74811435 3.87516105 1.04362821]
Return so far: -9
Action: [0.27025694]
State : [1.32772665 0.88286876 4.39697515 1.04362821]
Return so far: -8
Action: [-0.37371287]
State : [1.76916103 0.69557089 4.91878926 1.04362821]
Return so far: -7
Action: [-0.15408142]
State : [2.11694647 0.6181824 5.44060336 1.04362821]
Return so far: -6
Action: [-0.35667756]
State : [2.42603767 0.43953453 5.96241746 1.04362821]
Return so far: -5
Action: [0.3605174]
State : [2.64580494 0.61957347 6.48423156 1.04362821]
Return so far: -4
Action: [0.02915601]
State : [2.95559167 0.63384169 7.00604567 1.04362821]
Return so far: -3
Action: [-0.18476082]
State : [3.27251251 0.54114435 7.52785977 1.04362821]
Return so far: -2
Action: [-0.10722011]
State : [3.54308469 0.48726372 8.04967387 1.04362821]
Return so far: -1
Action: [-0.19868594]
State : [-5.47534374 0.90380545 -4.48167899 1.01001023]
Return so far: -1
Action: [0.09774178]
State : [-5.02344102 0.95222444 -3.97667387 1.01001023]
Return so far: -2
Action: [-0.22323345]
State : [-4.5473288 0.8401316 -3.47166876 1.01001023]
Return so far: -3
Action: [0.16124406]
State : [-4.127263 0.92033357 -2.96666364 1.01001023]
Return so far: -4
Action: [-0.31031874]
State : [-3.66709621 0.76471403 -2.46165853 1.01001023]
Return so far: -5
Action: [0.05278249]
State : [-3.28473919 0.79072292 -1.95665341 1.01001023]
Return so far: -6
Action: [-0.28830343]
State : [-2.88937773 0.64617584 -1.4516483 1.01001023]
Return so far: -7
Action: [0.27349025]
State : [-2.56628981 0.78259788 -0.94664318 1.01001023]
Return so far: -8
Action: [-0.28547978]
State : [-2.17499087 0.63946669 -0.44163807 1.01001023]
Return so far: -9
Action: [-0.39995655]
State : [-1.85525753 0.43916868 0.06336705 1.01001023]
Return so far: -10
Action: [0.30644426]
State : [-1.63567319 0.59217122 0.56837216 1.01001023]
Return so far: -11
Action: [0.11152203]
State : [-1.33958758 0.64763615 1.07337728 1.01001023]
Return so far: -12
Action: [0.20737062]
State : [-1.0157695 0.75099765 1.57838239 1.01001023]
Return so far: -13
Action: [0.31983605]
State : [-0.64027068 0.91054017 2.08338751 1.01001023]
Return so far: -14
Action: [-0.19925989]
State : [-0.18500059 0.81045496 2.58839262 1.01001023]
Return so far: -15
Action: [0.01331828]
State : [0.22022689 0.81670887 3.09339774 1.01001023]
Return so far: -14
Action: [0.33684063]
State : [0.62858133 0.98472083 3.59840285 1.01001023]
Return so far: -13
Action: [-0.16889553]
State : [1.12094174 0.89978071 4.10340797 1.01001023]
Return so far: -12
Action: [0.31236082]
State : [1.5708321 1.05551123 4.60841308 1.01001023]
Return so far: -11
Action: [-0.27486533]
State : [2.09858771 0.91755081 5.1134182 1.01001023]
Return so far: -10
Action: [0.2091695]
State : [2.55736311 1.02167679 5.61842331 1.01001023]
Return so far: -9
Action: [-0.16644743]
State : [3.06820151 0.93794223 6.12342843 1.01001023]
Return so far: -8
Action: [0.16380632]
State : [3.53717262 1.01937642 6.62843354 1.01001023]
Return so far: -7
Action: [-0.08911297]
State : [4.04686083 0.97431025 7.13343865 1.01001023]
Return so far: -6
Action: [0.3730062]
State : [4.53401596 1.16032619 7.63844377 1.01001023]
Return so far: -5
Action: [-0.10510566]
State : [-5.458255 0.9407955 -4.50341941 0.97437713]
Return so far: -1
Action: [-0.02784814]
State : [-4.98785725 0.92640103 -4.01623084 0.97437713]
Return so far: -2
Action: [0.14544293]
State : [-4.52465674 0.9986593 -3.52904228 0.97437713]
Return so far: -3
Action: [-0.14222209]
State : [-4.02532709 0.92704892 -3.04185371 0.97437713]
Return so far: -4
Action: [0.33878368]
State : [-3.56180263 1.09597724 -2.55466515 0.97437713]
Return so far: -5
Action: [0.36965987]
State : [-3.01381401 1.28025919 -2.06747659 0.97437713]
Return so far: -6
Action: [0.20747112]
State : [-2.37368441 1.38335461 -1.58028802 0.97437713]
Return so far: -7
Action: [-0.31605643]
State : [-1.68200711 1.22463472 -1.09309946 0.97437713]
Return so far: -8
Action: [-0.3799503]
State : [-1.06968975 1.03404725 -0.60591089 0.97437713]
Return so far: -9
Action: [-0.04081246]
State : [-0.55266612 1.01312399 -0.11872233 0.97437713]
Return so far: -10
Action: [-0.04461516]
State : [-0.04610413 0.99030985 0.36846623 0.97437713]
Return so far: -11
Action: [-0.23987833]
State : [0.4490508 0.86987553 0.8556548 0.97437713]
Return so far: -10
Action: [0.17704527]
State : [0.88398856 0.95796323 1.34284336 0.97437713]
Return so far: -9
Action: [-0.30099037]
State : [1.36297018 0.80698906 1.83003193 0.97437713]
Return so far: -8
Action: [0.32410228]
State : [1.76646471 0.96863671 2.31722049 0.97437713]
Return so far: -7
Action: [0.35543576]
State : [2.25078306 1.14587027 2.80440905 0.97437713]
Return so far: -6
Action: [0.3620885]
State : [2.8237182 1.32634158 3.29159762 0.97437713]
Return so far: -5
Action: [-0.3368689]
State : [3.48688899 1.15724396 3.77878618 0.97437713]
Return so far: -4
Action: [0.3120966]
State : [4.06551097 1.31271363 4.26597475 0.97437713]
Return so far: -3
Action: [-0.2728445]
State : [4.72186778 1.17563503 4.75316331 0.97437713]
Return so far: -2
Action: [-0.00184154]
State : [5.3096853 1.17412644 5.24035187 0.97437713]
Return so far: -1
Action: [0.20354824]
State : [5.89674852 1.2753135 5.72754044 0.97437713]
Return so far: 0
Action: [-0.0993875]
State : [6.53440527 1.22498209 6.214729 0.97437713]
Return so far: 1
Action: [0.03788785]
State : [7.14689631 1.24331352 6.70191756 0.97437713]
Return so far: 2
Action: [0.14021353]
State : [7.76855308 1.31279863 7.18910613 0.97437713]
Return so far: 3
Action: [0.07802759]
State : [-1.63301722 0.40916243 -1.66331284 -1.21223435]
Return so far: -1
Action: [0.33046454]
State : [-1.48457891 1.02663397 -1.53044884 -1.21223435]
Return so far: -2
Action: [0.09228346]
State : [-1.31303505 1.19732693 -1.39758485 -1.21223435]
Return so far: -3
Action: [-0.03231163]
State : [-1.13510392 1.13438135 -1.26472086 -1.21223435]
Return so far: -4
Action: [0.1802334]
State : [-0.95952819 1.46988238 -1.13185687 -1.21223435]
Return so far: -5
Action: [-0.17404187]
State : [-0.77139815 1.14112754 -0.99899288 -1.21223435]
Return so far: -6
Action: [-0.31580406]
State : [-0.59556998 0.54680419 -0.86612889 -1.21223435]
Return so far: -7
Action: [-0.26963028]
State : [-0.44198116 0.03933063 -0.7332649 -1.21223435]
Return so far: -8
Action: [0.06055067]
State : [-0.30738181 0.15103421 -0.6004009 -1.21223435]
Return so far: -9
Action: [-0.3311819]
State : [-0.16860255 -0.47161984 -0.46753691 -1.21223435]
Return so far: -10
Action: [-0.11509745]
State : [-0.05312277 -0.68891276 -0.33467292 -1.21223435]
Return so far: -9
Action: [-0.38082883]
State : [ 0.054226 -1.40420985 -0.20180893 -1.21223435]
Return so far: -8
Action: [-0.16248532]
State : [ 0.13480863 -1.70986492 -0.06894494 -1.21223435]
Return so far: -7
Action: [-0.39587656]
State : [ 0.20395377 -2.45285846 0.06391905 -1.21223435]
Return so far: -6
Action: [0.05325113]
State : [ 0.24529637 -2.35359177 0.19678304 -1.21223435]
Return so far: -5
Action: [0.3841403]
State : [ 0.29035349 -1.63412375 0.32964703 -1.21223435]
Return so far: -4
Action: [0.01613574]
State : [ 0.36233283 -1.60483912 0.46251103 -1.21223435]
Return so far: -3
Action: [-0.14909767]
State : [ 0.43540799 -1.88529876 0.59537502 -1.21223435]
Return so far: -2
Action: [-0.3930535]
State : [ 0.49798846 -2.62291278 0.72823901 -1.21223435]
Return so far: -1
Action: [0.33051294]
State : [ 0.5329677 -2.00383448 0.861103 -1.21223435]
Return so far: 0
Action: [0.27897942]
State : [ 0.59111261 -1.48166517 0.99396699 -1.21223435]
Return so far: 1
Action: [0.28623137]
State : [ 0.66879689 -0.94616319 1.12683098 -1.21223435]
Return so far: 2
Action: [0.06693257]
State : [ 0.76651944 -0.82200402 1.25969497 -1.21223435]
Return so far: 3
Action: [0.07720309]
State : [ 0.86888799 -0.67865487 1.39255897 -1.21223435]
Return so far: 4
Action: [-0.02737788]
State : [ 0.9766206 -0.73141417 1.52542296 -1.21223435]
Return so far: 5
Action: [-0.17159137]
State : [-1.60129505 -0.29571384 -1.66772534 -0.71271999]
Return so far: -1
Action: [0.24396574]
State : [-1.47923293 0.15996836 -1.53259886 -0.71271999]
Return so far: -2
Action: [-0.00237471]
State : [-1.34011936 0.15365815 -1.39747238 -0.71271999]
Return so far: -3
Action: [0.32496664]
State : [-1.20124191 0.76095163 -1.26234591 -0.71271999]
Return so far: -4
Action: [-0.27877057]
State : [-1.03963978 0.23623757 -1.12721943 -0.71271999]
Return so far: -5
Action: [-0.3054429]
State : [-0.89767224 -0.33821136 -0.99209296 -0.71271999]
Return so far: -6
Action: [0.34207687]
State : [-0.77720037 0.30140114 -0.85696648 -0.71271999]
Return so far: -7
Action: [0.07577825]
State : [-0.63279443 0.44151773 -0.72184001 -0.71271999]
Return so far: -8
Action: [0.3691626]
State : [-0.4831454 1.13151249 -0.58671353 -0.71271999]
Return so far: -9
Action: [0.25216246]
State : [-0.30767702 1.60184579 -0.45158705 -0.71271999]
Return so far: -10
Action: [0.05916549]
State : [-0.11460895 1.71017157 -0.31646058 -0.71271999]
Return so far: -11
Action: [-0.05719995]
State : [ 0.08251262 1.60031646 -0.1813341 -0.71271999]
Return so far: -10
Action: [-0.24155706]
State : [ 0.27552346 1.14493934 -0.04620763 -0.71271999]
Return so far: -9
Action: [-0.15142098]
State : [ 0.45149426 0.85874977 0.08891885 -0.71271999]
Return so far: -8
Action: [0.13501602]
State : [ 0.61675596 1.10962875 0.22404533 -0.71271999]
Return so far: -7
Action: [0.06481712]
State : [ 0.79140546 1.22879462 0.3591718 -0.71271999]
Return so far: -6
Action: [0.04327345]
State : [ 0.97051409 1.30751735 0.49429828 -0.71271999]
Return so far: -5
Action: [0.2582062]
State : [ 1.1525685 1.7890916 0.62942475 -0.71271999]
Return so far: -4
Action: [-0.01484966]
State : [ 1.35264323 1.75858257 0.76455123 -0.71271999]
Return so far: -3
Action: [0.34021488]
State : [ 1.55157632 2.39365638 0.89967771 -0.71271999]
Return so far: -2
Action: [0.20216684]
State : [ 1.77427364 2.76964195 1.03480418 -0.71271999]
Return so far: -1
Action: [-0.3626722]
State : [ 2.01104018 2.08665011 1.16993066 -0.71271999]
Return so far: 0
Action: [-0.31076756]
State : [ 2.22224944 1.50129491 1.30505713 -0.71271999]
Return so far: 1
Action: [-0.38294697]
State : [ 2.41155493 0.78093227 1.44018361 -0.71271999]
Return so far: 2
Action: [-0.2856166]
State : [ 2.57390473 0.24337533 1.57531008 -0.71271999]
Return so far: 3
Action: [0.05009854]
State : [-1.59519356 0.44850979 -1.66453034 -0.20387637]
Return so far: -1
Action: [-0.2503229]
State : [-1.44528288 -0.02272298 -1.52709912 -0.20387637]
Return so far: -2
Action: [0.36530513]
State : [-1.31300555 0.66027309 -1.38966791 -0.20387637]
Return so far: -3
Action: [0.30813998]
State : [-1.15517077 1.23577174 -1.25223669 -0.20387637]
Return so far: -4
Action: [0.12213445]
State : [-0.97580105 1.46231574 -1.11480547 -0.20387637]
Return so far: -5
Action: [-0.05441266]
State : [-0.78795415 1.35780934 -0.97737426 -0.20387637]
Return so far: -6
Action: [-0.17021033]
State : [-0.60401783 1.03629274 -0.83994304 -0.20387637]
Return so far: -7
Action: [0.3370976]
State : [-0.43211254 1.66588434 -0.70251183 -0.20387637]
Return so far: -8
Action: [-0.03073102]
State : [-0.23664818 1.60566732 -0.56508061 -0.20387637]
Return so far: -9
Action: [-0.19644323]
State : [-0.04343711 1.23485329 -0.42764939 -0.20387637]
Return so far: -8
Action: [0.24108353]
State : [ 0.13589823 1.6843675 -0.29021818 -0.20387637]
Return so far: -7
Action: [0.07423618]
State : [ 0.33205423 1.82090201 -0.15278696 -0.20387637]
Return so far: -6
Action: [0.01786379]
State : [ 0.53331929 1.85169834 -0.01535575 -0.20387637]
Return so far: -5
Action: [0.38338038]
State : [ 0.73573674 2.56763923 0.12207547 -0.20387637]
Return so far: -4
Action: [0.17248327]
State : [ 0.96494443 2.88789602 0.25950669 -0.20387637]
Return so far: -3
Action: [0.3418303]
State : [ 1.20613599 3.5254333 0.3969379 -0.20387637]
Return so far: -2
Action: [0.3123794]
State : [ 1.47118396 4.10744614 0.53436912 -0.20387637]
Return so far: -1
Action: [0.32263014]
State : [ 1.75801062 4.70838296 0.67180033 -0.20387637]
Return so far: 0
Action: [-0.02546094]
State : [ 2.0673241 4.65652345 0.80923155 -0.20387637]
Return so far: 1
Action: [-0.01544565]
State : [ 2.37469702 4.62346351 0.94666277 -0.20387637]
Return so far: 2
Action: [0.21540801]
State : [ 2.68083285 5.02315471 1.08409398 -0.20387637]
Return so far: 3
Action: [-0.10762177]
State : [ 3.00192496 4.81712754 1.2215252 -0.20387637]
Return so far: 4
Action: [-0.23180622]
State : [ 3.31530763 4.37841994 1.35895641 -0.20387637]
Return so far: 5
Action: [0.07394613]
State : [ 3.61227402 4.51306371 1.49638763 -0.20387637]
Return so far: 6
Action: [-0.1980579]
State : [ 3.91427873 4.13776928 1.63381885 -0.20387637]
Return so far: 7
Action: [0.1175654]
State : [-1.63008808 0.18713183 -1.6695346 -0.40352107]
Return so far: -1
Action: [-0.27136087]
State : [-1.48995807 -0.32340587 -1.53300765 -0.40352107]
Return so far: -2
Action: [0.3936422]
State : [-1.36893217 0.41285829 -1.3964807 -0.40352107]
Return so far: -3
Action: [0.18258287]
State : [-1.22035556 0.75312415 -1.25995375 -0.40352107]
Return so far: -4
Action: [-0.02309474]
State : [-1.05904633 0.70767772 -1.1234268 -0.40352107]
Return so far: -5
Action: [-0.227443]
State : [-0.89943768 0.2792037 -0.98689985 -0.40352107]
Return so far: -6
Action: [-0.11481177]
State : [-0.75586237 0.06207087 -0.8503729 -0.40352107]
Return so far: -7
Action: [-0.31624383]
State : [-0.62041209 -0.53253729 -0.71384594 -0.40352107]
Return so far: -8
Action: [0.11812914]
State : [-0.50721181 -0.31261709 -0.57731899 -0.40352107]
Return so far: -9
Action: [-0.3702342]
State : [-0.3857822 -1.00824271 -0.44079204 -0.40352107]
Return so far: -10
Action: [0.25621948]
State : [-0.29038264 -0.52923466 -0.30426509 -0.40352107]
Return so far: -11
Action: [-0.37819788]
State : [-0.17705878 -1.23967988 -0.16773814 -0.40352107]
Return so far: -12
Action: [0.09460293]
State : [-0.0903195 -1.06350593 -0.03121119 -0.40352107]
Return so far: -13
Action: [0.3391913]
State : [ 0.00301214 -0.42893979 0.10531577 -0.40352107]
Return so far: -12
Action: [-0.04847363]
State : [ 0.12008899 -0.52136787 0.24184272 -0.40352107]
Return so far: -11
Action: [0.23362938]
State : [ 0.23370722 -0.08494834 0.37836967 -0.40352107]
Return so far: -10
Action: [0.0876408]
State : [ 0.36365611 0.07759775 0.51489662 -0.40352107]
Return so far: -9
Action: [0.23238233]
State : [ 0.4996874 0.5113802 0.65142357 -0.40352107]
Return so far: -8
Action: [0.09415493]
State : [ 0.65195067 0.68583885 0.78795052 -0.40352107]
Return so far: -7
Action: [-0.15758997]
State : [ 0.81074211 0.38831507 0.92447748 -0.40352107]
Return so far: -6
Action: [0.09754763]
State : [ 0.95840032 0.56919485 1.06100443 -0.40352107]
Return so far: -5
Action: [-0.26048684]
State : [ 1.11282699 0.07884946 1.19753138 -0.40352107]
Return so far: -4
Action: [-0.27058876]
State : [ 1.24890512 -0.43018676 1.33405833 -0.40352107]
Return so far: -3
Action: [0.12892537]
State : [ 1.36593532 -0.19008023 1.47058528 -0.40352107]
Return so far: -2
Action: [0.20399965]
State : [ 1.49195021 0.19063281 1.60711223 -0.40352107]
Return so far: -1
Action: [0.32517058]
State : [-1.59886325 0.93411959 -1.67172575 -0.8163335 ]
Return so far: -1
Action: [0.30550537]
State : [-1.43078125 1.50454273 -1.53706857 -0.8163335 ]
Return so far: -2
Action: [-0.14236462]
State : [-1.24135422 1.23514948 -1.4024114 -0.8163335 ]
Return so far: -3
Action: [0.17069732]
State : [-1.06200779 1.55272476 -1.26775423 -0.8163335 ]
Return so far: -4
Action: [-0.20644659]
State : [-0.87077782 1.16318593 -1.13309706 -0.8163335 ]
Return so far: -5
Action: [-0.29607594]
State : [-0.69412423 0.60583186 -0.99843989 -0.8163335 ]
Return so far: -6
Action: [-0.00216614]
State : [-0.53832662 0.59968968 -0.86378271 -0.8163335 ]
Return so far: -7
Action: [0.22908613]
State : [-0.38275885 1.02703237 -0.72912554 -0.8163335 ]
Return so far: -8
Action: [0.10666961]
State : [-0.21120008 1.22469193 -0.59446837 -0.8163335 ]
Return so far: -9
Action: [-0.25099784]
State : [-0.03224497 0.7518059 -0.4598112 -0.8163335 ]
Return so far: -8
Action: [0.39578047]
State : [ 0.12901494 1.49154068 -0.32515403 -0.8163335 ]
Return so far: -7
Action: [-0.16660318]
State : [ 0.31795543 1.17671881 -0.19049685 -0.8163335 ]
Return so far: -6
Action: [0.208226]
State : [ 0.4951154 1.56467072 -0.05583968 -0.8163335 ]
Return so far: -5
Action: [0.18452892]
State : [ 0.68679239 1.90800854 0.07881749 -0.8163335 ]
Return so far: -4
Action: [0.38885581]
State : [ 0.89131695 2.63418495 0.21347466 -0.8163335 ]
Return so far: -3
Action: [-0.39368197]
State : [ 1.12301475 1.89313312 0.34813184 -0.8163335 ]
Return so far: -2
Action: [0.12471875]
State : [ 1.32698267 2.12419269 0.48278901 -0.8163335 ]
Return so far: -1
Action: [0.10864411]
State : [ 1.53959675 2.32500487 0.61744618 -0.8163335 ]
Return so far: 0
Action: [-0.02236246]
State : [ 1.75972515 2.28014514 0.75210335 -0.8163335 ]
Return so far: 1
Action: [0.29325396]
State : [ 1.97817492 2.82693005 0.88676052 -0.8163335 ]
Return so far: 2
Action: [0.06894767]
State : [ 2.21708516 2.95297996 1.0214177 -0.8163335 ]
Return so far: 3
Action: [-0.37590924]
State : [ 2.46071214 2.24508368 1.15607487 -0.8163335 ]
Return so far: 4
Action: [-0.24052139]
State : [ 2.67784992 1.79132554 1.29073204 -0.8163335 ]
Return so far: 5
Action: [-0.06305487]
State : [ 2.87800824 1.67045483 1.42538921 -0.8163335 ]
Return so far: 6
Action: [-0.01582614]
State : [ 3.07364363 1.63817468 1.56004638 -0.8163335 ]
Return so far: 7
2021-02-18 17:00:13.258589: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-02-18 17:00:13.260837: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-02-18 17:00:13.324937: W tensorflow/python/util/util.cc:348] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
***ITERATION**** 0
2021-02-18 17:00:14.811078: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2)
-----Learned models------
---Lengthscales---
GP0 GP1 GP2 GP3
0 13.417 23.148 11.128 1.127
1 7.770 30.391 14.226 1.182
2 11.727 20.329 9.497 1.104
3 9.651 16.972 6.971 1.074
4 8.773 1.330 6.207 1.048
---Variances---
GP0 GP1 GP2 GP3
0 0.027 0.682 0.006 8.989e-06
---Noises---
GP0 GP1 GP2 GP3
0 0.001 0.001 0.001 0.001
Controller's optimization: done in 16.3 seconds with reward=-55.106.
Randomising controller
Controller's optimization: done in 13.4 seconds with reward=-65.724.
Predicted episode's return: -50.48029418951719
Overall risk 0.015419795446969808
Mu is -300.0
bound1 0.2805718850286911 bound1 0.27177913168067597
Action: tf.Tensor([-0.02670297], shape=(1,), dtype=float64)
State : [-1.6324844 0.16763989 -1.68597504 -1.02978357]
Return so far: -1
Action: tf.Tensor([-0.09040831], shape=(1,), dtype=float64)
State : [-1.49308376 -0.00369293 -1.55228466 -1.02978357]
Return so far: -2
Action: tf.Tensor([-0.13064547], shape=(1,), dtype=float64)
State : [-1.36009433 -0.25036454 -1.41859428 -1.02978357]
Return so far: -3
Action: tf.Tensor([-0.14456655], shape=(1,), dtype=float64)
State : [-1.23633526 -0.52300784 -1.2849039 -1.02978357]
Return so far: -4
Action: tf.Tensor([-0.14328452], shape=(1,), dtype=float64)
State : [-1.12277839 -0.79311166 -1.15121353 -1.02978357]
Return so far: -5
Action: tf.Tensor([-0.14156022], shape=(1,), dtype=float64)
State : [-1.01932871 -1.05984823 -1.01752315 -1.02978357]
Return so far: -6
Action: tf.Tensor([-0.15086911], shape=(1,), dtype=float64)
State : [-0.9258602 -1.34390093 -0.88383277 -1.02978357]
Return so far: -7
Action: tf.Tensor([-0.17436545], shape=(1,), dtype=float64)
State : [-0.84302083 -1.67185544 -0.75014239 -1.02978357]
Return so far: -8
Action: tf.Tensor([-0.19886607], shape=(1,), dtype=float64)
State : [-0.7724534 -2.04557232 -0.61645201 -1.02978357]
Return so far: -9
Action: tf.Tensor([-0.17173102], shape=(1,), dtype=float64)
State : [-0.71587031 -2.36823775 -0.48276163 -1.02978357]
Return so far: -10
Action: tf.Tensor([-0.05955752], shape=(1,), dtype=float64)
State : [-0.67136123 -2.48047291 -0.34907126 -1.02978357]
Return so far: -11
Action: tf.Tensor([0.0558778], shape=(1,), dtype=float64)
State : [-0.63105195 -2.37626872 -0.21538088 -1.02978357]
Return so far: -12
Action: tf.Tensor([0.13345972], shape=(1,), dtype=float64)
State : [-0.58684338 -2.12668952 -0.0816905 -1.02978357]
Return so far: -13
Action: tf.Tensor([0.17546408], shape=(1,), dtype=float64)
State : [-0.53329567 -1.79849805 0.05199988 -1.02978357]
Return so far: -14
Action: tf.Tensor([0.19138984], shape=(1,), dtype=float64)
State : [-0.46746715 -1.44061785 0.18569026 -1.02978357]
Return so far: -15
Action: tf.Tensor([0.19464023], shape=(1,), dtype=float64)
State : [-0.38824689 -1.07682376 0.31938063 -1.02978357]
Return so far: -16
Action: tf.Tensor([0.19222204], shape=(1,), dtype=float64)
State : [-0.2954136 -0.71774447 0.45307101 -1.02978357]
Return so far: -17
Action: tf.Tensor([0.18603478], shape=(1,), dtype=float64)
State : [-0.18914371 -0.37044271 0.58676139 -1.02978357]
Return so far: -18
Action: tf.Tensor([0.17906943], shape=(1,), dtype=float64)
State : [-0.06987791 -0.03637112 0.72045177 -1.02978357]
Return so far: -17
Action: tf.Tensor([0.17446177], shape=(1,), dtype=float64)
State : [ 0.06188871 0.28889638 0.85414215 -1.02978357]
Return so far: -16
Action: tf.Tensor([0.17261326], shape=(1,), dtype=float64)
State : [ 0.20582672 0.61053622 0.98783253 -1.02978357]
Return so far: -15
Action: tf.Tensor([0.17144662], shape=(1,), dtype=float64)
State : [ 0.36180036 0.92982837 1.1215229 -1.02978357]
Return so far: -14
Action: tf.Tensor([0.16763262], shape=(1,), dtype=float64)
State : [ 0.5297218 1.24181154 1.25521328 -1.02978357]
Return so far: -13
Action: tf.Tensor([0.15762381], shape=(1,), dtype=float64)
State : [ 0.70931752 1.53487723 1.38890366 -1.02978357]
Return so far: -12
Action: tf.Tensor([0.13910466], shape=(1,), dtype=float64)
State : [ 0.89987965 1.7930823 1.52259404 -1.02978357]
Return so far: -11
***ITERATION**** 1
-----Learned models------
---Lengthscales---
GP0 GP1 GP2 GP3
0 14.286 24.069 11.492 1.119
1 7.968 31.365 14.810 1.182
2 12.690 21.251 9.922 1.107
3 9.803 17.103 7.041 1.069
4 8.841 1.353 6.241 1.041
---Variances---
GP0 GP1 GP2 GP3
0 0.026 0.688 0.006 7.419e-06
---Noises---
GP0 GP1 GP2 GP3
0 0.001 0.001 0.001 0.001
Controller's optimization: done in 13.9 seconds with reward=-52.055.
Randomising controller
Controller's optimization: done in 13.4 seconds with reward=-105.091.
Predicted episode's return: -47.79509029607208
Overall risk 0.01893441921138328
Mu is -225.0
bound1 0.2805718850286911 bound1 0.27177913168067597
Action: tf.Tensor([-0.06825868], shape=(1,), dtype=float64)
State : [-1.63153607 -0.07460798 -1.66930315 0.44099232]
Return so far: -1
Action: tf.Tensor([-0.13178437], shape=(1,), dtype=float64)
State : [-1.50120025 -0.32337899 -1.52895109 0.44099232]
Return so far: -2
Action: tf.Tensor([-0.16952747], shape=(1,), dtype=float64)
State : [-1.38017335 -0.64277497 -1.38859902 0.44099232]
Return so far: -3
Action: tf.Tensor([-0.18670123], shape=(1,), dtype=float64)
State : [-1.27109812 -0.99420343 -1.24824696 0.44099232]
Return so far: -4
Action: tf.Tensor([-0.19398819], shape=(1,), dtype=float64)
State : [-1.17517322 -1.35911556 -1.10789489 0.44099232]
Return so far: -5
Action: tf.Tensor([-0.19838623], shape=(1,), dtype=float64)
State : [-1.09290318 -1.73208935 -0.96754283 0.44099232]
Return so far: -6
Action: tf.Tensor([-0.19955883], shape=(1,), dtype=float64)
State : [-1.02458967 -2.1070747 -0.82719077 0.44099232]
Return so far: -7
Action: tf.Tensor([-0.18559647], shape=(1,), dtype=float64)
State : [-0.97030797 -2.45570012 -0.6868387 0.44099232]
Return so far: -8
Action: tf.Tensor([-0.13939958], shape=(1,), dtype=float64)
State : [-0.9290717 -2.7175553 -0.54648664 0.44099232]
Return so far: -9
Action: tf.Tensor([-0.06556365], shape=(1,), dtype=float64)
State : [-0.89763395 -2.84087426 -0.40613458 0.44099232]
Return so far: -10
Action: tf.Tensor([0.01150478], shape=(1,), dtype=float64)
State : [-0.87081075 -2.81966699 -0.26578251 0.44099232]
Return so far: -11
Action: tf.Tensor([0.07616423], shape=(1,), dtype=float64)
State : [-0.84319398 -2.67726635 -0.12543045 0.44099232]
Return so far: -12
Action: tf.Tensor([0.12121925], shape=(1,), dtype=float64)
State : [-0.81024863 -2.45048138 0.01492162 0.44099232]
Return so far: -13
Action: tf.Tensor([0.14289547], shape=(1,), dtype=float64)
State : [-0.76881708 -2.18317779 0.15527368 0.44099232]
Return so far: -14
Action: tf.Tensor([0.14220503], shape=(1,), dtype=float64)
State : [-0.71738313 -1.91730207 0.29562574 0.44099232]
Return so far: -15
Action: tf.Tensor([0.12387776], shape=(1,), dtype=float64)
State : [-0.65600021 -1.68591371 0.43597781 0.44099232]
Return so far: -16
Action: tf.Tensor([0.09927464], shape=(1,), dtype=float64)
State : [-0.58595883 -1.50075954 0.57632987 0.44099232]
Return so far: -17
Action: tf.Tensor([0.08150802], shape=(1,), dtype=float64)
State : [-0.50898906 -1.34900142 0.71668194 0.44099232]
Return so far: -18
Action: tf.Tensor([0.0742255], shape=(1,), dtype=float64)
State : [-0.42634055 -1.21097025 0.857034 0.44099232]
Return so far: -19
Action: tf.Tensor([0.07534924], shape=(1,), dtype=float64)
State : [-0.33852697 -1.07090164 0.99738606 0.44099232]
Return so far: -20
Action: tf.Tensor([0.08316942], shape=(1,), dtype=float64)
State : [-0.24547208 -0.91624417 1.13773813 0.44099232]
Return so far: -21
Action: tf.Tensor([0.09732351], shape=(1,), dtype=float64)
State : [-0.14662996 -0.73513221 1.27809019 0.44099232]
Return so far: -22
Action: tf.Tensor([0.1178737], shape=(1,), dtype=float64)
State : [-0.04101071 -0.51558954 1.41844225 0.44099232]
Return so far: -21
Action: tf.Tensor([0.14336719], shape=(1,), dtype=float64)
State : [ 0.07282375 -0.24836914 1.55879432 0.44099232]
Return so far: -20
Action: tf.Tensor([0.16803597], shape=(1,), dtype=float64)
State : [0.19665749 0.06495921 1.69914638 0.44099232]
Return so far: -19
***ITERATION**** 2
-----Learned models------
---Lengthscales---
GP0 GP1 GP2 GP3
0 14.672 24.252 11.840 1.091
1 8.200 32.147 15.556 1.148
2 13.352 21.947 10.481 1.088
3 11.809 19.451 8.081 1.075
4 8.865 1.350 6.247 1.031
---Variances---
GP0 GP1 GP2 GP3
0 0.025 0.667 0.005 6.228e-06
---Noises---
GP0 GP1 GP2 GP3
0 0.001 0.001 0.001 0.001
Controller's optimization: done in 22.8 seconds with reward=-50.095.
Randomising controller
Controller's optimization: done in 15.6 seconds with reward=-38.628.
Predicted episode's return: 96.31638345679198
Overall risk 0.7996681801788684
Mu is -168.75
bound1 0.2805718850286911 bound1 0.27177913168067597
Action: tf.Tensor([0.19987786], shape=(1,), dtype=float64)
State : [-1.61748361 0.40917949 -1.67330459 -1.30055272]
Return so far: -1
Action: tf.Tensor([0.19899513], shape=(1,), dtype=float64)
State : [-1.46904466 0.78021193 -1.54084063 -1.30055272]
Return so far: -2
Action: tf.Tensor([0.19871633], shape=(1,), dtype=float64)
State : [-1.30672181 1.15053624 -1.40837666 -1.30055272]
Return so far: -3
Action: tf.Tensor([0.19923625], shape=(1,), dtype=float64)
State : [-1.13054158 1.52164998 -1.2759127 -1.30055272]
Return so far: -4
Action: tf.Tensor([0.19977372], shape=(1,), dtype=float64)
State : [-0.94047441 1.89358566 -1.14344873 -1.30055272]
Return so far: -5
Action: tf.Tensor([0.19995588], shape=(1,), dtype=float64)
State : [-0.73648955 2.26567683 -1.01098477 -1.30055272]
Return so far: -6
Action: tf.Tensor([0.1999529], shape=(1,), dtype=float64)
State : [-0.51858119 2.63757636 -0.8785208 -1.30055272]
Return so far: -7
Action: tf.Tensor([0.19984481], shape=(1,), dtype=float64)
State : [-0.28675648 3.00908733 -0.74605684 -1.30055272]
Return so far: -8
Action: tf.Tensor([0.19980689], shape=(1,), dtype=float64)
State : [-0.04102999 3.38034147 -0.61359287 -1.30055272]
Return so far: -7
Action: tf.Tensor([0.19999147], shape=(1,), dtype=float64)
State : [ 0.2185887 3.75175596 -0.48112891 -1.30055272]
Return so far: -6
Action: tf.Tensor([0.19967219], shape=(1,), dtype=float64)
State : [ 0.49210557 4.12238626 -0.34866494 -1.30055272]
Return so far: -5
Action: tf.Tensor([0.19887246], shape=(1,), dtype=float64)
State : [ 0.77949128 4.49133215 -0.21620098 -1.30055272]
Return so far: -4
Action: tf.Tensor([0.1993392], shape=(1,), dtype=float64)
State : [ 1.08068281 4.86096848 -0.08373701 -1.30055272]
Return so far: -3
Action: tf.Tensor([0.19995396], shape=(1,), dtype=float64)
State : [ 1.39570598 5.23157234 0.04872695 -1.30055272]
Return so far: -2
Action: tf.Tensor([0.1984779], shape=(1,), dtype=float64)
State : [ 1.72459701 5.59922405 0.18119092 -1.30055272]
Return so far: -1
Action: tf.Tensor([0.19883608], shape=(1,), dtype=float64)
State : [ 2.06724542 5.96736332 0.31365488 -1.30055272]
Return so far: 0
Action: tf.Tensor([0.19903226], shape=(1,), dtype=float64)
State : [ 2.42366945 6.33568626 0.44611885 -1.30055272]
Return so far: 1
Action: tf.Tensor([0.17914849], shape=(1,), dtype=float64)
State : [ 2.793876 6.66655297 0.57858281 -1.30055272]
Return so far: 2
Action: tf.Tensor([0.1329373], shape=(1,), dtype=float64)
State : [ 3.17646344 6.91063148 0.71104678 -1.30055272]
Return so far: 3
Action: tf.Tensor([0.08326998], shape=(1,), dtype=float64)
State : [ 3.56818421 7.06148669 0.84351074 -1.30055272]
Return so far: 4
Action: tf.Tensor([0.04599163], shape=(1,), dtype=float64)
State : [ 3.96554992 7.14238829 0.97597471 -1.30055272]
Return so far: 5
Action: tf.Tensor([0.02263934], shape=(1,), dtype=float64)
State : [ 4.36594294 7.17947563 1.10843867 -1.30055272]
Return so far: 6
Action: tf.Tensor([0.00986247], shape=(1,), dtype=float64)
State : [ 4.76772375 7.19259423 1.24090264 -1.30055272]
Return so far: 7
Action: tf.Tensor([0.00376425], shape=(1,), dtype=float64)
State : [ 5.16999545 7.19427516 1.3733666 -1.30055272]
Return so far: 8
Action: tf.Tensor([0.00124945], shape=(1,), dtype=float64)
State : [ 5.57233006 7.19124125 1.50583057 -1.30055272]
Return so far: 9
[-0.02408419 -0.01764648 -0.01129296 -0.00476827 0.0020023 0.00893821
0.01588555 0.02265181 0.02897538 0.03450059 0.03877442 0.04124448
0.04128481 0.0381705 0.03097926 0.01874148 0.000668 -0.02415904
-0.05685443 -0.09747952 -0.14438537 -0.19544838 -0.24904043 -0.30420295
-0.36051435]
[ 0.00959173 0.0079489 0.00672585 0.00585775 0.0052745 0.00490075
0.00465537 0.00445117 0.00419491 0.00378739 0.00312324 0.00209151
0.00057785 -0.00153307 -0.00435711 -0.00801391 -0.0126305 -0.01833117
-0.02520095 -0.03324787 -0.04241142 -0.05261311 -0.06380111 -0.07596483
-0.08913025]
*********CHANGING***********
tf.Tensor([[-38.62762195]], shape=(1, 1), dtype=float64)
tf.Tensor([[-106.09962465]], shape=(1, 1), dtype=float64)
***ITERATION**** 3
Controller's optimization: done in 15.5 seconds with reward=-104.885.
Randomising controller
Controller's optimization: done in 20.2 seconds with reward=-109.064.
Predicted episode's return: 96.96360687478742
Overall risk 0.7974251461663486
Mu is -253.125
bound1 0.2805718850286911 bound1 0.27177913168067597
Action: tf.Tensor([0.19962836], shape=(1,), dtype=float64)
State : [-1.63210265 0.42057428 -1.65972677 -1.59835445]
Return so far: -1
Action: tf.Tensor([0.19952627], shape=(1,), dtype=float64)
State : [-1.48323731 0.79259664 -1.52861166 -1.59835445]
Return so far: -2
Action: tf.Tensor([0.1997537], shape=(1,), dtype=float64)
State : [-1.32045103 1.16485931 -1.39749655 -1.59835445]
Return so far: -3
Action: tf.Tensor([0.19997319], shape=(1,), dtype=float64)
State : [-1.14373483 1.53734729 -1.26638144 -1.59835445]
Return so far: -4
Action: tf.Tensor([0.19997469], shape=(1,), dtype=float64)
State : [-0.95308028 1.90965184 -1.13526633 -1.59835445]
Return so far: -5
Action: tf.Tensor([0.19988128], shape=(1,), dtype=float64)
State : [-0.74849423 2.28159513 -1.00415122 -1.59835445]
Return so far: -6
Action: tf.Tensor([0.19988804], shape=(1,), dtype=float64)
State : [-0.52999021 2.65336512 -0.87303611 -1.59835445]
Return so far: -7
Action: tf.Tensor([0.19997845], shape=(1,), dtype=float64)
State : [-0.2975747 3.0251187 -0.741921 -1.59835445]
Return so far: -8
Action: tf.Tensor([0.19997477], shape=(1,), dtype=float64)
State : [-0.05124831 3.39667951 -0.61080588 -1.59835445]
Return so far: -7
Action: tf.Tensor([0.1997143], shape=(1,), dtype=float64)
State : [ 0.20898174 3.76756628 -0.47969077 -1.59835445]
Return so far: -6
Action: tf.Tensor([0.19902743], shape=(1,), dtype=float64)
State : [ 0.48309022 4.13698007 -0.34857566 -1.59835445]
Return so far: -5
Action: tf.Tensor([0.19764152], shape=(1,), dtype=float64)
State : [ 0.77102203 4.50361127 -0.21746055 -1.59835445]
Return so far: -4
Action: tf.Tensor([0.19549447], shape=(1,), dtype=float64)
State : [ 1.07267304 4.86603451 -0.08634544 -1.59835445]
Return so far: -3
Action: tf.Tensor([0.19367431], shape=(1,), dtype=float64)
State : [ 1.38788578 5.22486467 0.04476967 -1.59835445]
Return so far: -2
Action: tf.Tensor([0.19461367], shape=(1,), dtype=float64)
State : [ 1.71652581 5.58527622 0.17588478 -1.59835445]
Return so far: -1
Action: tf.Tensor([0.19874274], shape=(1,), dtype=float64)
State : [ 2.05865229 5.95324751 0.30699989 -1.59835445]
Return so far: 0
Action: tf.Tensor([0.19840827], shape=(1,), dtype=float64)
State : [ 2.41454812 6.32040786 0.43811501 -1.59835445]
Return so far: 1
Action: tf.Tensor([0.18038601], shape=(1,), dtype=float64)
State : [ 2.78418295 6.65360194 0.56923012 -1.59835445]
Return so far: 2
Action: tf.Tensor([0.14354691], shape=(1,), dtype=float64)
State : [ 3.16628578 6.91757462 0.70034523 -1.59835445]
Return so far: 3
Action: tf.Tensor([0.10170803], shape=(1,), dtype=float64)
State : [ 3.55826635 7.10298843 0.83146034 -1.59835445]
Return so far: 4
Action: tf.Tensor([0.06604432], shape=(1,), dtype=float64)
State : [ 3.95718504 7.221458 0.96257545 -1.59835445]
Return so far: 5
Action: tf.Tensor([0.03976759], shape=(1,), dtype=float64)
State : [ 4.36053682 7.29061267 1.09369056 -1.59835445]
Return so far: 6
Action: tf.Tensor([0.02217026], shape=(1,), dtype=float64)
State : [ 4.76647634 7.32674662 1.22480567 -1.59835445]
Return so far: 7
Action: tf.Tensor([0.01136907], shape=(1,), dtype=float64)
State : [ 5.17376797 7.3426157 1.35592078 -1.59835445]
Return so far: 8
Action: tf.Tensor([0.00532549], shape=(1,), dtype=float64)
State : [ 5.58165342 7.34714816 1.4870359 -1.59835445]
Return so far: 9
[-0.00902104 -0.00302946 0.00311848 0.00953398 0.01623067 0.02314362
0.03014003 0.03701113 0.04346077 0.04910356 0.05346588 0.05599117
0.05606571 0.05305346 0.04629594 0.03504209 0.01831618 -0.00512106
-0.03635526 -0.07547864 -0.12137714 -0.17242978 -0.22714263 -0.28439869
-0.34349081]
[-5.33494123e-03 -5.63181566e-03 -5.50894020e-03 -5.03272674e-03
-4.27422754e-03 -3.30952449e-03 -2.22011025e-03 -1.09325583e-03
-2.22852154e-05 8.93472023e-04 1.54915471e-03 1.83485537e-03
1.63566800e-03 8.31917647e-04 -6.99792788e-04 -3.08629314e-03
-6.45806700e-03 -1.09407660e-02 -1.66291400e-02 -2.35574823e-02
-3.16970514e-02 -4.09872144e-02 -5.13736706e-02 -6.28292259e-02
-7.53572648e-02]
*********CHANGING***********
tf.Tensor([[-104.88463325]], shape=(1, 1), dtype=float64)
tf.Tensor([[-205.80875331]], shape=(1, 1), dtype=float64)
***ITERATION**** 4
Controller's optimization: done in 16.4 seconds with reward=-205.385.
Randomising controller
Controller's optimization: done in 17.6 seconds with reward=-206.446.
Predicted episode's return: 97.21029694156654
Overall risk 0.796959166027458
Mu is -379.6875
bound1 0.2805718850286911 bound1 0.27177913168067597
Action: tf.Tensor([0.18970969], shape=(1,), dtype=float64)
State : [-1.60522783 0.59988939 -1.66405917 1.83454728]
Return so far: -1
Action: tf.Tensor([0.18290909], shape=(1,), dtype=float64)
State : [-1.44965259 0.94067323 -1.51739518 1.83454728]
Return so far: -2
Action: tf.Tensor([0.15851101], shape=(1,), dtype=float64)
State : [-1.28132534 1.23555254 -1.37073119 1.83454728]
Return so far: -3
Action: tf.Tensor([0.10106473], shape=(1,), dtype=float64)
State : [-1.10196383 1.42260151 -1.2240672 1.83454728]
Return so far: -4
Action: tf.Tensor([0.00913749], shape=(1,), dtype=float64)
State : [-0.91560301 1.43723956 -1.07740322 1.83454728]
Return so far: -5
Action: tf.Tensor([-0.08390294], shape=(1,), dtype=float64)
State : [-0.72869445 1.27746624 -0.93073923 1.83454728]
Return so far: -6
Action: tf.Tensor([-0.13974662], shape=(1,), dtype=float64)
State : [-0.54776454 1.01309397 -0.78407524 1.83454728]
Return so far: -7
Action: tf.Tensor([-0.15469066], shape=(1,), dtype=float64)
State : [-0.37672734 0.72084131 -0.63741125 1.83454728]
Return so far: -8
Action: tf.Tensor([-0.13856477], shape=(1,), dtype=float64)
State : [-0.21662612 0.45896272 -0.49074727 1.83454728]
Return so far: -9
Action: tf.Tensor([-0.09640344], shape=(1,), dtype=float64)
State : [-0.0663243 0.27624637 -0.34408328 1.83454728]
Return so far: -8
Action: tf.Tensor([-0.04353048], shape=(1,), dtype=float64)
State : [ 0.07714035 0.19273163 -0.19741929 1.83454728]
Return so far: -7
Action: tf.Tensor([-0.00101983], shape=(1,), dtype=float64)
State : [ 0.21747991 0.18894475 -0.05075531 1.83454728]
Return so far: -6
Action: tf.Tensor([0.02074116], shape=(1,), dtype=float64)
State : [0.35767777 0.22595068 0.09590868 1.83454728]
Return so far: -5
Action: tf.Tensor([0.02096169], shape=(1,), dtype=float64)
State : [0.49926037 0.26335149 0.24257267 1.83454728]
Return so far: -4
Action: tf.Tensor([0.00267669], shape=(1,), dtype=float64)
State : [0.6422425 0.26645841 0.38923666 1.83454728]
Return so far: -3
Action: tf.Tensor([-0.02965763], shape=(1,), dtype=float64)
State : [0.78534088 0.20895317 0.53590064 1.83454728]
Return so far: -2
Action: tf.Tensor([-0.0710351], shape=(1,), dtype=float64)
State : [0.92628745 0.07391473 0.68256463 1.83454728]
Return so far: -1
Action: tf.Tensor([-0.11586053], shape=(1,), dtype=float64)
State : [ 1.06218092 -0.14508135 0.82922862 1.83454728]
Return so far: 0
Action: tf.Tensor([-0.1568635], shape=(1,), dtype=float64)
State : [ 1.18987965 -0.4408279 0.97589261 1.83454728]
Return so far: 1
Action: tf.Tensor([-0.18572506], shape=(1,), dtype=float64)
State : [ 1.30651166 -0.7905275 1.12255659 1.83454728]
Return so far: 2
Action: tf.Tensor([-0.1984091], shape=(1,), dtype=float64)
State : [ 1.41005804 -1.16382847 1.26922058 1.83454728]
Return so far: 3
Action: tf.Tensor([-0.19976473], shape=(1,), dtype=float64)
State : [ 1.49963565 -1.53948389 1.41588457 1.83454728]
Return so far: 4
Action: tf.Tensor([-0.19859494], shape=(1,), dtype=float64)
State : [ 1.57515638 -1.91275871 1.56254856 1.83454728]
Return so far: 5
Action: tf.Tensor([-0.19930174], shape=(1,), dtype=float64)
State : [ 1.6367093 -2.2871718 1.70921254 1.83454728]
Return so far: 6
Action: tf.Tensor([-0.19984214], shape=(1,), dtype=float64)
State : [ 1.68425184 -2.66241066 1.85587653 1.83454728]
Return so far: 7
[-0.02848653 -0.02990443 -0.03045049 -0.02954419 -0.02544991 -0.01418988
0.01055284 0.05508921 0.12303389 0.21504328 0.32950299 0.46288356
0.6108246 0.76961665 0.93691792 1.111808 1.29461033 1.48660845
1.68964392 1.90563203 2.13607924 2.38168943 2.64226635 2.91709805
3.20551691]
[ 0.01454633 -0.00129964 -0.01672596 -0.03179908 -0.04659018 -0.0611755
-0.07563681 -0.09006171 -0.10454386 -0.119183 -0.13408483 -0.14936088
-0.16512837 -0.18150941 -0.19862917 -0.21661463 -0.23559544 -0.25570199
-0.27705015 -0.29971287 -0.32370062 -0.34897199 -0.37546699 -0.40313739
-0.43196078]
*********CHANGING***********
tf.Tensor([[-205.38513641]], shape=(1, 1), dtype=float64)
tf.Tensor([[-356.68285309]], shape=(1, 1), dtype=float64)

Process finished with exit code 0