{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.096771001815796, "min": 1.7978801727294922, "max": 2.198930501937866, "count": 201 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41599.9375, "min": 690.385986328125, "max": 47759.4921875, "count": 201 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.16470588235294, "min": 10.0, "max": 59.811764705882354, "count": 201 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19776.0, "min": 40.0, "max": 20336.0, "count": 201 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1554.956835449178, "min": 1486.59631400373, "max": 1554.956835449178, "count": 201 }, "SoccerTwos.Self-play.ELO.sum": { "value": 264342.6620263603, "min": 3003.063497265889, "max": 374218.4854370862, "count": 201 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 201 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 201 }, "SoccerTwos.Step.mean": { "value": 14999958.0, "min": 13009978.0, "max": 14999958.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 14999958.0, "min": 13009978.0, "max": 14999958.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.043893054127693176, "min": -0.09020467102527618, "max": 0.07734177261590958, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.461819171905518, "min": -19.213594436645508, "max": 15.545696258544922, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04128238558769226, "min": -0.08795364946126938, "max": 0.0766124352812767, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.018005847930908, "min": -18.734127044677734, "max": 15.399099349975586, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.11723058854832369, "min": -0.3401765263696232, "max": 0.18128047151678411, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 19.929200053215027, "min": -72.45760011672974, "max": 39.10800004005432, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.11723058854832369, "min": -0.3401765263696232, "max": 0.18128047151678411, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 19.929200053215027, "min": -72.45760011672974, "max": 39.10800004005432, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018280768686478648, "min": 0.011735149780724896, "max": 0.024575366786060236, "count": 97 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018280768686478648, "min": 0.011735149780724896, "max": 0.024575366786060236, "count": 97 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1402090256412824, "min": 0.13842538744211197, "max": 0.16264882385730745, "count": 97 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1402090256412824, "min": 0.13842538744211197, "max": 0.16264882385730745, "count": 97 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.14100217719872793, "min": 0.1402094433705012, "max": 0.16492244303226472, "count": 97 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.14100217719872793, "min": 0.1402094433705012, "max": 0.16492244303226472, "count": 97 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00019999999999999996, "count": 97 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00019999999999999996, "min": 0.00019999999999999996, "max": 0.00019999999999999996, "count": 97 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 97 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 97 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 97 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 97 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691413445", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu", "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": "1691420891" }, "total": 7446.493744302001, "count": 1, "self": 0.44090754500211915, "children": { "run_training.setup": { "total": 0.05116394600008789, "count": 1, "self": 0.05116394600008789 }, "TrainerController.start_learning": { "total": 7446.001672810999, "count": 1, "self": 4.463491247934144, "children": { "TrainerController._reset_env": { "total": 2.2937364919985157, "count": 10, "self": 2.2937364919985157 }, "TrainerController.advance": { "total": 7439.116317394068, "count": 142012, "self": 3.6368457870757993, "children": { "env_step": { "total": 2941.015872404006, "count": 142012, "self": 2456.025975177389, "children": { "SubprocessEnvManager._take_step": { "total": 482.48543693276815, "count": 142012, "self": 17.11533814368886, "children": { "TorchPolicy.evaluate": { "total": 465.3700987890793, "count": 250632, "self": 465.3700987890793 } } }, "workers": { "total": 2.504460293849206, "count": 142012, "self": 0.0, "children": { "worker_root": { "total": 7436.180982305729, "count": 142012, "is_parallel": true, "self": 5390.057720905652, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00443643999960841, "count": 2, "is_parallel": true, "self": 0.0011098709992438671, "children": { "_process_rank_one_or_two_observation": { "total": 0.003326569000364543, "count": 8, "is_parallel": true, "self": 0.003326569000364543 } } }, "UnityEnvironment.step": { "total": 0.048430476000248746, "count": 1, "is_parallel": true, "self": 0.0010615390001476044, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007993300000634918, "count": 1, "is_parallel": true, "self": 0.0007993300000634918 }, "communicator.exchange": { "total": 0.04133742700014409, "count": 1, "is_parallel": true, "self": 0.04133742700014409 }, "steps_from_proto": { "total": 0.00523217999989356, "count": 2, "is_parallel": true, "self": 0.0005823099995723169, "children": { "_process_rank_one_or_two_observation": { "total": 0.004649870000321243, "count": 8, "is_parallel": true, "self": 0.004649870000321243 } } } } } } }, "steps_from_proto": { "total": 0.01876272900335607, "count": 18, "is_parallel": true, "self": 0.003684774000703328, "children": { "_process_rank_one_or_two_observation": { "total": 0.015077955002652743, "count": 72, "is_parallel": true, "self": 0.015077955002652743 } } }, "UnityEnvironment.step": { "total": 2046.104498671074, "count": 142011, "is_parallel": true, "self": 125.091241453154, "children": { "UnityEnvironment._generate_step_input": { "total": 65.50758502101417, "count": 142011, "is_parallel": true, "self": 65.50758502101417 }, "communicator.exchange": { "total": 1475.5032075824838, "count": 142011, "is_parallel": true, "self": 1475.5032075824838 }, "steps_from_proto": { "total": 380.002464614422, "count": 284022, "is_parallel": true, "self": 69.75164025852473, "children": { "_process_rank_one_or_two_observation": { "total": 310.2508243558973, "count": 1136088, "is_parallel": true, "self": 310.2508243558973 } } } } } } } } } } }, "trainer_advance": { "total": 4494.463599202985, "count": 142012, "self": 29.215439991813582, "children": { "process_trajectory": { "total": 712.2678581821747, "count": 142012, "self": 711.6323160651764, "children": { "RLTrainer._checkpoint": { "total": 0.6355421169982947, "count": 5, "self": 0.6355421169982947 } } }, "_update_policy": { "total": 3752.980301028997, "count": 97, "self": 324.84123214594683, "children": { "TorchPOCAOptimizer.update": { "total": 3428.13906888305, "count": 2910, "self": 3428.13906888305 } } } } } } }, "trainer_threads": { "total": 6.299997039604932e-07, "count": 1, "self": 6.299997039604932e-07 }, "TrainerController._save_models": { "total": 0.12812704699899768, "count": 1, "self": 0.0025897599989548326, "children": { "RLTrainer._checkpoint": { "total": 0.12553728700004285, "count": 1, "self": 0.12553728700004285 } } } } } } }