{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2010748386383057, "min": 3.125300407409668, "max": 3.2930920124053955, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 307303.1875, "min": 282047.6875, "max": 380839.5, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 911.4814814814815, "min": 597.609756097561, "max": 997.12, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 98440.0, "min": 97228.0, "max": 103384.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.9982579271607, "min": 1195.9461036196167, "max": 1221.9759648492238, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7187.989547562964, "min": 4815.290022352901, "max": 67659.85144552909, "count": 100 }, "SoccerTwos.Step.mean": { "value": 4999006.0, "min": 49298.0, "max": 4999006.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 4999006.0, "min": 49298.0, "max": 4999006.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.005989752244204283, "min": -0.020525911822915077, "max": 0.087294802069664, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.3234466314315796, "min": -1.4622992277145386, "max": 5.412277698516846, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006024852395057678, "min": -0.02027856558561325, "max": 0.08779024332761765, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.3253420293331146, "min": -1.46644926071167, "max": 5.442995071411133, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.014903702117778637, "min": -0.3030208965290838, "max": 0.1328193553453011, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.8047999143600464, "min": -20.302400067448616, "max": 8.234800031408668, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.014903702117778637, "min": -0.3030208965290838, "max": 0.1328193553453011, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.8047999143600464, "min": -20.302400067448616, "max": 8.234800031408668, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017588941159192475, "min": 0.01358264352408393, "max": 0.022225120673020782, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.03517788231838495, "min": 0.02716528704816786, "max": 0.06667536201906235, "count": 100 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.032043584814346e-06, "min": 1.032043584814346e-06, "max": 0.0063071357435546815, "count": 100 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.064087169628692e-06, "min": 2.064087169628692e-06, "max": 0.01644136217655614, "count": 100 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.0190511574137418e-06, "min": 1.0190511574137418e-06, "max": 0.006349796561213831, "count": 100 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.0381023148274836e-06, "min": 2.0381023148274836e-06, "max": 0.01644182266124214, "count": 100 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 100 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0010000000000000002, "min": 0.0010000000000000002, "max": 0.0015000000000000005, "count": 100 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 100 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.40000000000000013, "min": 0.40000000000000013, "max": 0.6000000000000002, "count": 100 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 100 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.015000000000000003, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685981895", "python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]", "command_line_arguments": "/home/jordi.casalsg@local.eurecat.org/Projects/huggingface_rl_course/.venv/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env=ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1685991256" }, "total": 9360.728360399, "count": 1, "self": 0.2698277909985336, "children": { "run_training.setup": { "total": 0.009219612999913807, "count": 1, "self": 0.009219612999913807 }, "TrainerController.start_learning": { "total": 9360.449312995, "count": 1, "self": 6.83880282789687, "children": { "TrainerController._reset_env": { "total": 2.395111159999942, "count": 20, "self": 2.395111159999942 }, "TrainerController.advance": { "total": 9351.069702443105, "count": 322600, "self": 6.7799339637513185, "children": { "env_step": { "total": 5966.13806850438, "count": 322600, "self": 5015.16742263604, "children": { "SubprocessEnvManager._take_step": { "total": 946.5662092797893, "count": 322600, "self": 40.277690839007846, "children": { "TorchPolicy.evaluate": { "total": 906.2885184407814, "count": 640360, "self": 906.2885184407814 } } }, "workers": { "total": 4.4044365885501975, "count": 322600, "self": 0.0, "children": { "worker_root": { "total": 9350.874216507473, "count": 322600, "is_parallel": true, "self": 5168.509147819968, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001656623000599211, "count": 2, "is_parallel": true, "self": 0.0003833420005321386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012732810000670725, "count": 8, "is_parallel": true, "self": 0.0012732810000670725 } } }, "UnityEnvironment.step": { "total": 0.018593669999972917, "count": 1, "is_parallel": true, "self": 0.0004340109999247943, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042529999973339727, "count": 1, "is_parallel": true, "self": 0.00042529999973339727 }, "communicator.exchange": { "total": 0.016364310999961162, "count": 1, "is_parallel": true, "self": 0.016364310999961162 }, "steps_from_proto": { "total": 0.0013700480003535631, "count": 2, "is_parallel": true, "self": 0.00027673399836203316, "children": { "_process_rank_one_or_two_observation": { "total": 0.00109331400199153, "count": 8, "is_parallel": true, "self": 0.00109331400199153 } } } } } } }, "UnityEnvironment.step": { "total": 4182.324120445506, "count": 322599, "is_parallel": true, "self": 226.06505653365912, "children": { "UnityEnvironment._generate_step_input": { "total": 182.2265820848761, "count": 322599, "is_parallel": true, "self": 182.2265820848761 }, "communicator.exchange": { "total": 3018.4676932755547, "count": 322599, "is_parallel": true, "self": 3018.4676932755547 }, "steps_from_proto": { "total": 755.5647885514163, "count": 645198, "is_parallel": true, "self": 140.88628420069745, "children": { "_process_rank_one_or_two_observation": { "total": 614.6785043507189, "count": 2580792, "is_parallel": true, "self": 614.6785043507189 } } } } }, "steps_from_proto": { "total": 0.040948241998194135, "count": 38, "is_parallel": true, "self": 0.008140299991282518, "children": { "_process_rank_one_or_two_observation": { "total": 0.03280794200691162, "count": 152, "is_parallel": true, "self": 0.03280794200691162 } } } } } } } } }, "trainer_advance": { "total": 3378.151699974973, "count": 322600, "self": 52.74593217319125, "children": { "process_trajectory": { "total": 504.36863245177483, "count": 322600, "self": 502.78837369577377, "children": { "RLTrainer._checkpoint": { "total": 1.580258756001058, "count": 10, "self": 1.580258756001058 } } }, "_update_policy": { "total": 2821.037135350007, "count": 232, "self": 693.2836983750385, "children": { "TorchPOCAOptimizer.update": { "total": 2127.7534369749683, "count": 6969, "self": 2127.7534369749683 } } } } } } }, "trainer_threads": { "total": 8.150018402375281e-07, "count": 1, "self": 8.150018402375281e-07 }, "TrainerController._save_models": { "total": 0.14569574899724103, "count": 1, "self": 0.0010777259994938504, "children": { "RLTrainer._checkpoint": { "total": 0.14461802299774718, "count": 1, "self": 0.14461802299774718 } } } } } } }