| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.678034782409668, | |
| "min": 1.5968852043151855, | |
| "max": 3.233602523803711, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 33077.421875, | |
| "min": 17696.080078125, | |
| "max": 117138.6796875, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 91.75925925925925, | |
| "min": 62.217948717948715, | |
| "max": 999.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19820.0, | |
| "min": 2580.0, | |
| "max": 30880.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1836.438429277303, | |
| "min": 1179.2443037592927, | |
| "max": 1882.37162875756, | |
| "count": 1640 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 198335.35036194872, | |
| "min": 2361.124059228245, | |
| "max": 287966.5509843448, | |
| "count": 1640 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 17769978.0, | |
| "min": 179784.0, | |
| "max": 17769978.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 17769978.0, | |
| "min": 179784.0, | |
| "max": 17769978.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.06006792560219765, | |
| "min": -0.13460491597652435, | |
| "max": 0.27712440490722656, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -6.427268028259277, | |
| "min": -16.538028717041016, | |
| "max": 29.072328567504883, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0632435604929924, | |
| "min": -0.13357815146446228, | |
| "max": 0.27661097049713135, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -6.76706075668335, | |
| "min": -16.533781051635742, | |
| "max": 29.783599853515625, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.14345046738597833, | |
| "min": -0.5008588227279046, | |
| "max": 0.6801075255999001, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -15.349200010299683, | |
| "min": -38.858800172805786, | |
| "max": 73.20900005102158, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.14345046738597833, | |
| "min": -0.5008588227279046, | |
| "max": 0.6801075255999001, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -15.349200010299683, | |
| "min": -38.858800172805786, | |
| "max": 73.20900005102158, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1760 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.021148083967273124, | |
| "min": 0.012226460961974226, | |
| "max": 0.02482709277770482, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.021148083967273124, | |
| "min": 0.012226460961974226, | |
| "max": 0.02482709277770482, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.058767483830451966, | |
| "min": 1.941374570435528e-07, | |
| "max": 0.07228325821459293, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.058767483830451966, | |
| "min": 1.941374570435528e-07, | |
| "max": 0.07228325821459293, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.06154869928956032, | |
| "min": 2.1960907531592966e-07, | |
| "max": 0.07937255546450615, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.06154869928956032, | |
| "min": 2.1960907531592966e-07, | |
| "max": 0.07937255546450615, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.00030000000000000003, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.00030000000000000003, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.19999999999999996, | |
| "min": 0.1999999999999999, | |
| "max": 0.19999999999999996, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.19999999999999996, | |
| "min": 0.1999999999999999, | |
| "max": 0.19999999999999996, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005, | |
| "min": 0.005, | |
| "max": 0.005, | |
| "count": 846 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005, | |
| "min": 0.005, | |
| "max": 0.005, | |
| "count": 846 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1679283741", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "C:\\Users\\Harikrishnan\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", | |
| "mlagents_version": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.0.0+cu117", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1679323876" | |
| }, | |
| "total": 40135.4429809, | |
| "count": 1, | |
| "self": 2.7203401000006124, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.2814753000000003, | |
| "count": 1, | |
| "self": 0.2814753000000003 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 40132.4411655, | |
| "count": 1, | |
| "self": 24.566991302461247, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 27.113152699983004, | |
| "count": 89, | |
| "self": 27.113152699983004 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 40080.46692929755, | |
| "count": 1171992, | |
| "self": 24.480452696843713, | |
| "children": { | |
| "env_step": { | |
| "total": 26651.92155879969, | |
| "count": 1171992, | |
| "self": 16748.34745229964, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 9884.468393799361, | |
| "count": 1171992, | |
| "self": 214.8578931963948, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 9669.610500602967, | |
| "count": 2224116, | |
| "self": 9669.610500602967 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 19.10571270068916, | |
| "count": 1171992, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 40063.883836604226, | |
| "count": 1171992, | |
| "is_parallel": true, | |
| "self": 26597.65168740455, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.17281169997980683, | |
| "count": 178, | |
| "is_parallel": true, | |
| "self": 0.03303249997880897, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.13977920000099786, | |
| "count": 712, | |
| "is_parallel": true, | |
| "self": 0.13977920000099786 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 13466.059337499697, | |
| "count": 1171992, | |
| "is_parallel": true, | |
| "self": 924.8286633054868, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 685.6071762989832, | |
| "count": 1171992, | |
| "is_parallel": true, | |
| "self": 685.6071762989832 | |
| }, | |
| "communicator.exchange": { | |
| "total": 9345.10972820142, | |
| "count": 1171992, | |
| "is_parallel": true, | |
| "self": 9345.10972820142 | |
| }, | |
| "steps_from_proto": { | |
| "total": 2510.5137696938073, | |
| "count": 2343984, | |
| "is_parallel": true, | |
| "self": 480.9454844945235, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 2029.5682851992838, | |
| "count": 9375936, | |
| "is_parallel": true, | |
| "self": 2029.5682851992838 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 13404.064917801014, | |
| "count": 1171992, | |
| "self": 202.5390362991966, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 4284.44833050177, | |
| "count": 1171992, | |
| "self": 4274.55963380176, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 9.8886967000102, | |
| "count": 35, | |
| "self": 9.8886967000102 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 8917.077551000046, | |
| "count": 847, | |
| "self": 4489.795613900346, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 4427.2819370996995, | |
| "count": 42320, | |
| "self": 4427.2819370996995 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 3.2000025385059416e-06, | |
| "count": 1, | |
| "self": 3.2000025385059416e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.2940890000027139, | |
| "count": 1, | |
| "self": 0.06316930000321008, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.2309196999995038, | |
| "count": 1, | |
| "self": 0.2309196999995038 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |