{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.252148151397705, "min": 3.2340750694274902, "max": 3.2956032752990723, "count": 22 }, "SoccerTwos.Policy.Entropy.sum": { "value": 62233.10546875, "min": 27394.943359375, "max": 110437.109375, "count": 22 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 841.8333333333334, "min": 438.1818181818182, "max": 999.0, "count": 22 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20204.0, "min": 16556.0, "max": 24620.0, "count": 22 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.712235612661, "min": 1198.096716181842, "max": 1204.96588437155, "count": 19 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4810.848942450644, "min": 2397.5438868584306, "max": 12030.489174378994, "count": 19 }, "SoccerTwos.Step.mean": { "value": 219448.0, "min": 9328.0, "max": 219448.0, "count": 22 }, "SoccerTwos.Step.sum": { "value": 219448.0, "min": 9328.0, "max": 219448.0, "count": 22 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.021987518295645714, "min": -0.03358123451471329, "max": -0.00914370734244585, "count": 22 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.26385021209716797, "min": -0.3737238049507141, "max": -0.1097244918346405, "count": 22 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.025403909385204315, "min": -0.035054437816143036, "max": -0.009414930827915668, "count": 22 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.3048469126224518, "min": -0.48784586787223816, "max": -0.10248959809541702, "count": 22 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 22 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 22 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3333333333333333, "min": -0.521013331413269, "max": 0.1428000032901764, "count": 22 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.0, "min": -7.815199971199036, "max": 1.7136000394821167, "count": 22 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3333333333333333, "min": -0.521013331413269, "max": 0.1428000032901764, "count": 22 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.0, "min": -7.815199971199036, "max": 1.7136000394821167, "count": 22 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019089772222408406, "min": 0.014227441156981513, "max": 0.019250484396858763, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019089772222408406, "min": 0.014227441156981513, "max": 0.019250484396858763, "count": 10 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00303266728684927, "min": 3.1557437978335656e-05, "max": 0.005675278091803193, "count": 10 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00303266728684927, "min": 3.1557437978335656e-05, "max": 0.005675278091803193, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003077593092651417, "min": 3.051361230366941e-05, "max": 0.005773659151357909, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003077593092651417, "min": 3.051361230366941e-05, "max": 0.005773659151357909, "count": 10 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 10 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 10 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 10 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 10 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 10 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692630068", "python_version": "3.9.17 (main, Jul 5 2023, 15:35:09) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/maxph2211/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.app --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", "numpy_version": "1.21.2", "end_time_seconds": "1692630365" }, "total": 296.670284458, "count": 1, "self": 0.15351054100000283, "children": { "run_training.setup": { "total": 0.013190542000000027, "count": 1, "self": 0.013190542000000027 }, "TrainerController.start_learning": { "total": 296.503583375, "count": 1, "self": 0.10988081000192551, "children": { "TrainerController._reset_env": { "total": 1.6036085840000207, "count": 2, "self": 1.6036085840000207 }, "TrainerController.advance": { "total": 294.5489405649981, "count": 15271, "self": 0.10133990499599577, "children": { "env_step": { "total": 142.389375107002, "count": 15271, "self": 122.13004312600218, "children": { "SubprocessEnvManager._take_step": { "total": 20.162998269997207, "count": 15271, "self": 0.5817577979946584, "children": { "TorchPolicy.evaluate": { "total": 19.58124047200255, "count": 30328, "self": 19.58124047200255 } } }, "workers": { "total": 0.09633371100261234, "count": 15270, "self": 0.0, "children": { "worker_root": { "total": 294.5319253670018, "count": 15270, "is_parallel": true, "self": 190.35275932700335, "children": { "steps_from_proto": { "total": 0.001865914999996665, "count": 4, "is_parallel": true, "self": 0.00035421000005775305, "children": { "_process_rank_one_or_two_observation": { "total": 0.001511704999938912, "count": 16, "is_parallel": true, "self": 0.001511704999938912 } } }, "UnityEnvironment.step": { "total": 104.17730012499847, "count": 15270, "is_parallel": true, "self": 6.711494018002739, "children": { "UnityEnvironment._generate_step_input": { "total": 3.179639326997007, "count": 15270, "is_parallel": true, "self": 3.179639326997007 }, "communicator.exchange": { "total": 79.02621381300065, "count": 15270, "is_parallel": true, "self": 79.02621381300065 }, "steps_from_proto": { "total": 15.259952966998078, "count": 30540, "is_parallel": true, "self": 2.4347930950026964, "children": { "_process_rank_one_or_two_observation": { "total": 12.825159871995382, "count": 122160, "is_parallel": true, "self": 12.825159871995382 } } } } } } } } } } }, "trainer_advance": { "total": 152.05822555300006, "count": 15270, "self": 1.4833567860010817, "children": { "process_trajectory": { "total": 21.506046055999043, "count": 15270, "self": 21.506046055999043 }, "_update_policy": { "total": 129.06882271099994, "count": 10, "self": 14.724975051999323, "children": { "TorchPOCAOptimizer.update": { "total": 114.34384765900062, "count": 300, "self": 114.34384765900062 } } } } } } }, "trainer_threads": { "total": 7.499999696847226e-07, "count": 1, "self": 7.499999696847226e-07 }, "TrainerController._save_models": { "total": 0.24115266600000496, "count": 1, "self": 0.0023205410000173288, "children": { "RLTrainer._checkpoint": { "total": 0.23883212499998763, "count": 1, "self": 0.23883212499998763 } } } } } } }