{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8351892232894897, "min": 1.807372808456421, "max": 3.2956910133361816, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36175.25, "min": 22560.74609375, "max": 105462.109375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.13333333333333, "min": 36.61363636363637, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19376.0, "min": 11532.0, "max": 28532.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1612.8594744114228, "min": 1198.250783323078, "max": 1636.152168249531, "count": 485 }, "SoccerTwos.Self-play.ELO.sum": { "value": 338700.4896263988, "min": 2396.501566646156, "max": 414883.5255077923, "count": 485 }, "SoccerTwos.Step.mean": { "value": 4999944.0, "min": 9282.0, "max": 4999944.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999944.0, "min": 9282.0, "max": 4999944.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017896011471748352, "min": -0.15194953978061676, "max": 0.18754254281520844, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.758162498474121, "min": -31.90940284729004, "max": 34.82117462158203, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.015916641801595688, "min": -0.15419496595859528, "max": 0.18863549828529358, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.3424947261810303, "min": -32.380943298339844, "max": 36.080955505371094, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0027638083412533715, "min": -0.5020250007510185, "max": 0.4428923053619189, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.580399751663208, "min": -73.3568000793457, "max": 56.46060001850128, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0027638083412533715, "min": -0.5020250007510185, "max": 0.4428923053619189, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.580399751663208, "min": -73.3568000793457, "max": 56.46060001850128, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014864107087487356, "min": 0.010403966914357929, "max": 0.02378533055598382, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014864107087487356, "min": 0.010403966914357929, "max": 0.02378533055598382, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11244653364022573, "min": 5.493518146977294e-05, "max": 0.1350829099615415, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11244653364022573, "min": 5.493518146977294e-05, "max": 0.1350829099615415, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11461577539642652, "min": 5.708877542929258e-05, "max": 0.13852139959732693, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11461577539642652, "min": 5.708877542929258e-05, "max": 0.13852139959732693, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680570444", "python_version": "3.9.5 (default, Nov 23 2021, 15:27:38) \n[GCC 9.3.0]", "command_line_arguments": "/mnt/c/Users/aymen/Documents/__work/course/HuggingFace-RL/AIvsAI/ml-agents/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680597382" }, "total": 26937.3257186, "count": 1, "self": 1.124178900001425, "children": { "run_training.setup": { "total": 0.18766459999824292, "count": 1, "self": 0.18766459999824292 }, "TrainerController.start_learning": { "total": 26936.0138751, "count": 1, "self": 9.611341998446733, "children": { "TrainerController._reset_env": { "total": 5.573190900016925, "count": 25, "self": 5.573190900016925 }, "TrainerController.advance": { "total": 26920.270721301542, "count": 343629, "self": 10.256154102753499, "children": { "env_step": { "total": 7044.852353100552, "count": 343629, "self": 5432.703721301834, "children": { "SubprocessEnvManager._take_step": { "total": 1605.9436684988614, "count": 343629, "self": 68.15418350081018, "children": { "TorchPolicy.evaluate": { "total": 1537.7894849980512, "count": 630192, "self": 1537.7894849980512 } } }, "workers": { "total": 6.2049632998568995, "count": 343629, "self": 0.0, "children": { "worker_root": { "total": 26907.239525102093, "count": 343629, "is_parallel": true, "self": 22586.369257003502, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009276099997805431, "count": 2, "is_parallel": true, "self": 0.00545419999252772, "children": { "_process_rank_one_or_two_observation": { "total": 0.003821900005277712, "count": 8, "is_parallel": true, "self": 0.003821900005277712 } } }, "UnityEnvironment.step": { "total": 0.03227329999936046, "count": 1, "is_parallel": true, "self": 0.0007169999989855569, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006582999994861893, "count": 1, "is_parallel": true, "self": 0.0006582999994861893 }, "communicator.exchange": { "total": 0.02903860000151326, "count": 1, "is_parallel": true, "self": 0.02903860000151326 }, "steps_from_proto": { "total": 0.001859399999375455, "count": 2, "is_parallel": true, "self": 0.00037960000190651044, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014797999974689446, "count": 8, "is_parallel": true, "self": 0.0014797999974689446 } } } } } } }, "UnityEnvironment.step": { "total": 4320.817081798599, "count": 343628, "is_parallel": true, "self": 285.40069440166553, "children": { "UnityEnvironment._generate_step_input": { "total": 192.27680339682775, "count": 343628, "is_parallel": true, "self": 192.27680339682775 }, "communicator.exchange": { "total": 3116.120760798982, "count": 343628, "is_parallel": true, "self": 3116.120760798982 }, "steps_from_proto": { "total": 727.0188232011242, "count": 687256, "is_parallel": true, "self": 141.1821268977801, "children": { "_process_rank_one_or_two_observation": { "total": 585.8366963033441, "count": 2749024, "is_parallel": true, "self": 585.8366963033441 } } } } }, "steps_from_proto": { "total": 0.05318629999237601, "count": 48, "is_parallel": true, "self": 0.01001250002082088, "children": { "_process_rank_one_or_two_observation": { "total": 0.04317379997155513, "count": 192, "is_parallel": true, "self": 0.04317379997155513 } } } } } } } } }, "trainer_advance": { "total": 19865.162214098236, "count": 343629, "self": 68.79791769751318, "children": { "process_trajectory": { "total": 2756.091131000594, "count": 343629, "self": 2751.3016344005955, "children": { "RLTrainer._checkpoint": { "total": 4.789496599998529, "count": 10, "self": 4.789496599998529 } } }, "_update_policy": { "total": 17040.27316540013, "count": 240, "self": 858.6222066001683, "children": { "TorchPOCAOptimizer.update": { "total": 16181.65095879996, "count": 7200, "self": 16181.65095879996 } } } } } } }, "trainer_threads": { "total": 1.2999953469261527e-06, "count": 1, "self": 1.2999953469261527e-06 }, "TrainerController._save_models": { "total": 0.5586196000003838, "count": 1, "self": 0.10836009999911766, "children": { "RLTrainer._checkpoint": { "total": 0.45025950000126613, "count": 1, "self": 0.45025950000126613 } } } } } } }