{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.183866262435913, "min": 3.1576008796691895, "max": 3.2451469898223877, "count": 80 }, "SoccerTwos.Policy.Entropy.sum": { "value": 147731.390625, "min": 32274.576171875, "max": 147731.390625, "count": 80 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 528.2, "min": 389.6666666666667, "max": 999.0, "count": 80 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21128.0, "min": 4676.0, "max": 31968.0, "count": 80 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 82 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 82 }, "SoccerTwos.Step.mean": { "value": 1309252.0, "min": 509914.0, "max": 1309252.0, "count": 81 }, "SoccerTwos.Step.sum": { "value": 1309252.0, "min": 509914.0, "max": 1309252.0, "count": 81 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007248410955071449, "min": -0.016149107366800308, "max": 0.007384084165096283, "count": 81 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.13771981000900269, "min": -0.16149106621742249, "max": 0.07860517501831055, "count": 81 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00707031786441803, "min": -0.016183573752641678, "max": 0.007944553159177303, "count": 81 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.13433603942394257, "min": -0.16183573007583618, "max": 0.07944553345441818, "count": 81 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 81 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 81 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.38606666773557663, "max": 0.24750769138336182, "count": 81 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -4.6328000128269196, "max": 3.2175999879837036, "count": 81 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.38606666773557663, "max": 0.24750769138336182, "count": 81 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -4.6328000128269196, "max": 3.2175999879837036, "count": 81 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1211.7637330361702, "min": 1202.8442763085673, "max": 1211.7637330361702, "count": 42 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2423.5274660723403, "min": 2405.6885526171345, "max": 7247.163809551618, "count": 42 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016080106038134544, "min": 0.010803807491902262, "max": 0.019793145587512603, "count": 37 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016080106038134544, "min": 0.010803807491902262, "max": 0.019793145587512603, "count": 37 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 7.310748022367382e-07, "min": 5.97159252417138e-07, "max": 0.002651917798599849, "count": 37 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 7.310748022367382e-07, "min": 5.97159252417138e-07, "max": 0.002651917798599849, "count": 37 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 7.017144450098082e-07, "min": 6.43051701369283e-07, "max": 0.002660218292536835, "count": 37 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 7.017144450098082e-07, "min": 6.43051701369283e-07, "max": 0.002660218292536835, "count": 37 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 37 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 37 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 37 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 37 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 37 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689795572", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\User\\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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1689800125" }, "total": 4552.5900939, "count": 1, "self": 4.528436600000532, "children": { "run_training.setup": { "total": 0.12988880000000025, "count": 1, "self": 0.12988880000000025 }, "TrainerController.start_learning": { "total": 4547.9317685, "count": 1, "self": 2.441726900019603, "children": { "TrainerController._reset_env": { "total": 3.9429609999990745, "count": 6, "self": 3.9429609999990745 }, "TrainerController.advance": { "total": 4541.208982099982, "count": 53312, "self": 2.7120177999777297, "children": { "env_step": { "total": 1871.9676023000193, "count": 53312, "self": 1446.537583399981, "children": { "SubprocessEnvManager._take_step": { "total": 423.9763628000451, "count": 53312, "self": 16.19581090012082, "children": { "TorchPolicy.evaluate": { "total": 407.78055189992426, "count": 105910, "self": 407.78055189992426 } } }, "workers": { "total": 1.4536560999931547, "count": 53311, "self": 0.0, "children": { "worker_root": { "total": 4540.639477399994, "count": 53311, "is_parallel": true, "self": 3382.275085500032, "children": { "steps_from_proto": { "total": 0.015660300000250427, "count": 12, "is_parallel": true, "self": 0.003938999999730797, "children": { "_process_rank_one_or_two_observation": { "total": 0.01172130000051963, "count": 48, "is_parallel": true, "self": 0.01172130000051963 } } }, "UnityEnvironment.step": { "total": 1158.3487315999612, "count": 53311, "is_parallel": true, "self": 58.515838100003975, "children": { "UnityEnvironment._generate_step_input": { "total": 47.16620979997619, "count": 53311, "is_parallel": true, "self": 47.16620979997619 }, "communicator.exchange": { "total": 852.6608494999962, "count": 53311, "is_parallel": true, "self": 852.6608494999962 }, "steps_from_proto": { "total": 200.0058341999848, "count": 106622, "is_parallel": true, "self": 41.84823450001252, "children": { "_process_rank_one_or_two_observation": { "total": 158.15759969997228, "count": 426488, "is_parallel": true, "self": 158.15759969997228 } } } } } } } } } } }, "trainer_advance": { "total": 2666.529361999985, "count": 53311, "self": 17.578268899951127, "children": { "process_trajectory": { "total": 366.78948090003337, "count": 53311, "self": 366.0611124000332, "children": { "RLTrainer._checkpoint": { "total": 0.7283685000001441, "count": 2, "self": 0.7283685000001441 } } }, "_update_policy": { "total": 2282.161612200001, "count": 37, "self": 247.92242620000297, "children": { "TorchPOCAOptimizer.update": { "total": 2034.239185999998, "count": 1125, "self": 2034.239185999998 } } } } } } }, "trainer_threads": { "total": 2.6999996407539584e-06, "count": 1, "self": 2.6999996407539584e-06 }, "TrainerController._save_models": { "total": 0.3380957999997918, "count": 1, "self": 0.021577899999101646, "children": { "RLTrainer._checkpoint": { "total": 0.31651790000069013, "count": 1, "self": 0.31651790000069013 } } } } } } }