{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.9164624810218811, "min": 0.8767052888870239, "max": 3.2909445762634277, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 18534.537109375, "min": 16952.37890625, "max": 74243.7109375, "count": 1000 }, "SoccerTwos.Step.mean": { "value": 9999949.0, "min": 9920.0, "max": 9999949.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999949.0, "min": 9920.0, "max": 9999949.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01673899032175541, "min": -0.20364925265312195, "max": 0.2616649866104126, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.6949775218963623, "min": -31.770320892333984, "max": 33.754783630371094, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016239335760474205, "min": -0.20775189995765686, "max": 0.2576749920845032, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.614532947540283, "min": -33.65580749511719, "max": 33.240074157714844, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 71.15384615384616, "min": 54.19565217391305, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18500.0, "min": 4468.0, "max": 30572.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1623.3708270474929, "min": 1191.0006940996452, "max": 1651.7492341518662, "count": 978 }, "SoccerTwos.Self-play.ELO.sum": { "value": 211038.20751617406, "min": 2384.630339602702, "max": 281718.4384865869, "count": 978 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.047053433556593104, "min": -0.6989142852170127, "max": 0.5635547165600758, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.163999795913696, "min": -52.371999859809875, "max": 54.50040012598038, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.047053433556593104, "min": -0.6989142852170127, "max": 0.5635547165600758, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.163999795913696, "min": -52.371999859809875, "max": 54.50040012598038, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.051063387057123086, "min": 0.03554979374651642, "max": 0.06648090017649035, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.10212677411424617, "min": 0.03554979374651642, "max": 0.12563409694024208, "count": 1000 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0805555042810738, "min": 3.552480529004735e-08, "max": 0.2019519372843206, "count": 1000 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1611110085621476, "min": 7.10496105800947e-08, "max": 0.4039038745686412, "count": 1000 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08055311075101296, "min": 3.6489922587238744e-08, "max": 0.22241845258201162, "count": 1000 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.16110622150202591, "min": 7.297984517447749e-08, "max": 0.44483690516402324, "count": 1000 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.282999571799897e-07, "min": 4.282999571799897e-07, "max": 0.0009994092000590795, "count": 1000 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 8.565999143599794e-07, "min": 8.565999143599794e-07, "max": 0.0019970470002953003, "count": 1000 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10003853799999998, "min": 0.10003853799999998, "max": 0.18994682800000004, "count": 1000 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20007707599999996, "min": 0.10076496399999998, "max": 0.37973423, "count": 1000 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.213671799999995e-05, "min": 1.213671799999995e-05, "max": 0.004997051908, "count": 1000 }, "SoccerTwos.Policy.Beta.sum": { "value": 2.42734359999999e-05, "min": 2.42734359999999e-05, "max": 0.009985264530000003, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715187404", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/guillaume/miniconda3/envs/aiVSai/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SowwerTwos-1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715202552" }, "total": 15147.973795295002, "count": 1, "self": 0.5099053880039719, "children": { "run_training.setup": { "total": 0.012307361997955013, "count": 1, "self": 0.012307361997955013 }, "TrainerController.start_learning": { "total": 15147.451582545, "count": 1, "self": 8.327006502186123, "children": { "TrainerController._reset_env": { "total": 3.469118672001059, "count": 167, "self": 3.469118672001059 }, "TrainerController.advance": { "total": 15135.59851007381, "count": 676149, "self": 8.718800398906751, "children": { "env_step": { "total": 11330.201897299637, "count": 676149, "self": 9137.230246284707, "children": { "SubprocessEnvManager._take_step": { "total": 2187.9567473920615, "count": 676149, "self": 57.54992742979812, "children": { "TorchPolicy.evaluate": { "total": 2130.4068199622634, "count": 1263852, "self": 2130.4068199622634 } } }, "workers": { "total": 5.014903622868587, "count": 676149, "self": 0.0, "children": { "worker_root": { "total": 15121.878172009536, "count": 676149, "is_parallel": true, "self": 7104.35424575943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027981000021100044, "count": 2, "is_parallel": true, "self": 0.0006888390198582783, "children": { "_process_rank_one_or_two_observation": { "total": 0.002109260982251726, "count": 8, "is_parallel": true, "self": 0.002109260982251726 } } }, "UnityEnvironment.step": { "total": 0.01820575999590801, "count": 1, "is_parallel": true, "self": 0.0008359630010090768, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000688052001351025, "count": 1, "is_parallel": true, "self": 0.000688052001351025 }, "communicator.exchange": { "total": 0.014278050999564584, "count": 1, "is_parallel": true, "self": 0.014278050999564584 }, "steps_from_proto": { "total": 0.0024036939939833246, "count": 2, "is_parallel": true, "self": 0.00046658799692522734, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019371059970580973, "count": 8, "is_parallel": true, "self": 0.0019371059970580973 } } } } } } }, "UnityEnvironment.step": { "total": 8017.138054214149, "count": 676148, "is_parallel": true, "self": 446.86225431098865, "children": { "UnityEnvironment._generate_step_input": { "total": 312.05068689021573, "count": 676148, "is_parallel": true, "self": 312.05068689021573 }, "communicator.exchange": { "total": 5983.6880813461685, "count": 676148, "is_parallel": true, "self": 5983.6880813461685 }, "steps_from_proto": { "total": 1274.5370316667759, "count": 1352296, "is_parallel": true, "self": 240.64140516377665, "children": { "_process_rank_one_or_two_observation": { "total": 1033.8956265029992, "count": 5409184, "is_parallel": true, "self": 1033.8956265029992 } } } } }, "steps_from_proto": { "total": 0.3858720359567087, "count": 332, "is_parallel": true, "self": 0.07392294886813033, "children": { "_process_rank_one_or_two_observation": { "total": 0.3119490870885784, "count": 1328, "is_parallel": true, "self": 0.3119490870885784 } } } } } } } } }, "trainer_advance": { "total": 3796.6778123752665, "count": 676149, "self": 65.98897389340709, "children": { "process_trajectory": { "total": 1043.6479575689518, "count": 676149, "self": 1042.2234857939693, "children": { "RLTrainer._checkpoint": { "total": 1.4244717749825213, "count": 20, "self": 1.4244717749825213 } } }, "_update_policy": { "total": 2687.0408809129076, "count": 1911, "self": 808.2067167750138, "children": { "TorchPOCAOptimizer.update": { "total": 1878.8341641378938, "count": 115008, "self": 1878.8341641378938 } } } } } } }, "trainer_threads": { "total": 7.880007615312934e-07, "count": 1, "self": 7.880007615312934e-07 }, "TrainerController._save_models": { "total": 0.05694650900113629, "count": 1, "self": 0.0022177779974299483, "children": { "RLTrainer._checkpoint": { "total": 0.054728731003706343, "count": 1, "self": 0.054728731003706343 } } } } } } }