{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7292778491973877, "min": 1.6640934944152832, "max": 1.7962404489517212, "count": 49 }, "SoccerTwos.Policy.Entropy.sum": { "value": 17209.7734375, "min": 12596.701171875, "max": 22191.23046875, "count": 49 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.955555555555556, "min": 40.69767441860465, "max": 81.16129032258064, "count": 49 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 9712.0, "min": 7000.0, "max": 10684.0, "count": 49 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1508.5287919842883, "min": 1490.143744573098, "max": 1513.876588566888, "count": 49 }, "SoccerTwos.Self-play.ELO.sum": { "value": 135767.59127858595, "min": 92431.31073084784, "max": 180006.0418777591, "count": 49 }, "SoccerTwos.Step.mean": { "value": 6754998.0, "min": 6514982.0, "max": 6754998.0, "count": 49 }, "SoccerTwos.Step.sum": { "value": 6754998.0, "min": 6514982.0, "max": 6754998.0, "count": 49 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011795819737017155, "min": -0.13557730615139008, "max": 0.0849948599934578, "count": 49 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.0616238117218018, "min": -11.795226097106934, "max": 6.544604301452637, "count": 49 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00861634686589241, "min": -0.14430177211761475, "max": 0.08878348767757416, "count": 49 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.7754712104797363, "min": -12.554253578186035, "max": 6.836328506469727, "count": 49 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 49 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 49 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.05251555575264825, "min": -0.2765686741794448, "max": 0.3353449278983517, "count": 49 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.726400017738342, "min": -22.95519995689392, "max": 28.378599762916565, "count": 49 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05251555575264825, "min": -0.2765686741794448, "max": 0.3353449278983517, "count": 49 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.726400017738342, "min": -22.95519995689392, "max": 28.378599762916565, "count": 49 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 49 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 49 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017573047970654444, "min": 0.014597583053182461, "max": 0.021161130908876658, "count": 11 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017573047970654444, "min": 0.014597583053182461, "max": 0.021161130908876658, "count": 11 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.13159407824277877, "min": 0.12053721149762471, "max": 0.13899534344673156, "count": 11 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.13159407824277877, "min": 0.12053721149762471, "max": 0.13899534344673156, "count": 11 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1348268409570058, "min": 0.12216988056898118, "max": 0.1415509695808093, "count": 11 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1348268409570058, "min": 0.12216988056898118, "max": 0.1415509695808093, "count": 11 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 11 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 11 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 11 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 11 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 11 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 11 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694301044", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\F:\\ProgramData\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1694302469" }, "total": 1424.2489313, "count": 1, "self": 0.010233900000002905, "children": { "run_training.setup": { "total": 0.13890439999999948, "count": 1, "self": 0.13890439999999948 }, "TrainerController.start_learning": { "total": 1424.099793, "count": 1, "self": 0.596130299996048, "children": { "TrainerController._reset_env": { "total": 4.470021500000097, "count": 3, "self": 4.470021500000097 }, "TrainerController.advance": { "total": 1418.707166400004, "count": 17241, "self": 0.584840800009033, "children": { "env_step": { "total": 408.37141819999925, "count": 17241, "self": 297.42648760000975, "children": { "SubprocessEnvManager._take_step": { "total": 110.57506159999487, "count": 17241, "self": 3.8856886999988234, "children": { "TorchPolicy.evaluate": { "total": 106.68937289999604, "count": 31108, "self": 106.68937289999604 } } }, "workers": { "total": 0.369868999994619, "count": 17241, "self": 0.0, "children": { "worker_root": { "total": 1360.326164599992, "count": 17241, "is_parallel": true, "self": 1132.4555731999756, "children": { "steps_from_proto": { "total": 0.007380800000023058, "count": 6, "is_parallel": true, "self": 0.0016224999997893619, "children": { "_process_rank_one_or_two_observation": { "total": 0.005758300000233696, "count": 24, "is_parallel": true, "self": 0.005758300000233696 } } }, "UnityEnvironment.step": { "total": 227.8632106000163, "count": 17241, "is_parallel": true, "self": 11.888181800012006, "children": { "UnityEnvironment._generate_step_input": { "total": 12.338912099999533, "count": 17241, "is_parallel": true, "self": 12.338912099999533 }, "communicator.exchange": { "total": 164.6181298999897, "count": 17241, "is_parallel": true, "self": 164.6181298999897 }, "steps_from_proto": { "total": 39.01798680001505, "count": 34482, "is_parallel": true, "self": 8.702775300027241, "children": { "_process_rank_one_or_two_observation": { "total": 30.31521149998781, "count": 137928, "is_parallel": true, "self": 30.31521149998781 } } } } } } } } } } }, "trainer_advance": { "total": 1009.7509073999959, "count": 17241, "self": 4.084613499997772, "children": { "process_trajectory": { "total": 152.83068689999814, "count": 17241, "self": 152.83068689999814 }, "_update_policy": { "total": 852.835607, "count": 12, "self": 72.28850790000251, "children": { "TorchPOCAOptimizer.update": { "total": 780.5470990999975, "count": 357, "self": 780.5470990999975 } } } } } } }, "trainer_threads": { "total": 1.9999999949504854e-06, "count": 1, "self": 1.9999999949504854e-06 }, "TrainerController._save_models": { "total": 0.3264727999999195, "count": 1, "self": 0.053011699999842676, "children": { "RLTrainer._checkpoint": { "total": 0.27346110000007684, "count": 1, "self": 0.27346110000007684 } } } } } } }