{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3524861335754395, "min": 1.273009181022644, "max": 3.295694351196289, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27439.23828125, "min": 21367.3828125, "max": 117663.6328125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 66.21333333333334, "min": 41.95652173913044, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19864.0, "min": 11364.0, "max": 29888.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1730.6058005600182, "min": 1184.2240249207669, "max": 1738.5369938735437, "count": 4995 }, "SoccerTwos.Self-play.ELO.sum": { "value": 259590.87008400273, "min": 2378.833707141451, "max": 385664.4527445863, "count": 4995 }, "SoccerTwos.Step.mean": { "value": 49999838.0, "min": 9394.0, "max": 49999838.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999838.0, "min": 9394.0, "max": 49999838.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017002170905470848, "min": -0.1568985879421234, "max": 0.18458378314971924, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.5333235263824463, "min": -26.430835723876953, "max": 29.766475677490234, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.015842989087104797, "min": -0.1604020893573761, "max": 0.18738055229187012, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.360605478286743, "min": -26.812332153320312, "max": 29.786434173583984, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06777986664099982, "min": -0.5714285714285714, "max": 0.5262178223912078, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -10.099200129508972, "min": -68.25759994983673, "max": 68.7684001326561, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06777986664099982, "min": -0.5714285714285714, "max": 0.5262178223912078, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -10.099200129508972, "min": -68.25759994983673, "max": 68.7684001326561, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017783529602456837, "min": 0.010097010507403562, "max": 0.02682568621627676, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017783529602456837, "min": 0.010097010507403562, "max": 0.02682568621627676, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0855464110771815, "min": 0.0003626643415676275, "max": 0.1272841068605582, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0855464110771815, "min": 0.0003626643415676275, "max": 0.1272841068605582, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08659987250963846, "min": 0.00037397446625012283, "max": 0.13016245663166046, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08659987250963846, "min": 0.00037397446625012283, "max": 0.13016245663166046, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675446105", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/sgoodfriend/miniconda3/envs/hf-marl-py39/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=baseline2 --no-graphics", "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": "1675855131" }, "total": 228730.148462333, "count": 1, "self": 0.5280049990105908, "children": { "run_training.setup": { "total": 0.03200166700000007, "count": 1, "self": 0.03200166700000007 }, "TrainerController.start_learning": { "total": 228729.588455667, "count": 1, "self": 44.46990310653928, "children": { "TrainerController._reset_env": { "total": 13.601097214076475, "count": 250, "self": 13.601097214076475 }, "TrainerController.advance": { "total": 228671.4408075974, "count": 3440053, "self": 41.627754303161055, "children": { "env_step": { "total": 182449.39058015824, "count": 3440053, "self": 175824.06173692524, "children": { "SubprocessEnvManager._take_step": { "total": 6595.9809881145, "count": 3440053, "self": 191.12584248775602, "children": { "TorchPolicy.evaluate": { "total": 6404.855145626744, "count": 6280888, "self": 6404.855145626744 } } }, "workers": { "total": 29.34785511850678, "count": 3440053, "self": 0.0, "children": { "worker_root": { "total": 228649.66797696945, "count": 3440053, "is_parallel": true, "self": 58157.9814848855, "children": { "steps_from_proto": { "total": 0.42265932286341346, "count": 500, "is_parallel": true, "self": 0.04849137167099937, "children": { "_process_rank_one_or_two_observation": { "total": 0.3741679511924141, "count": 2000, "is_parallel": true, "self": 0.3741679511924141 } } }, "UnityEnvironment.step": { "total": 170491.2638327611, "count": 3440053, "is_parallel": true, "self": 439.6987958837999, "children": { "UnityEnvironment._generate_step_input": { "total": 2946.9687258522936, "count": 3440053, "is_parallel": true, "self": 2946.9687258522936 }, "communicator.exchange": { "total": 161121.75380775216, "count": 3440053, "is_parallel": true, "self": 161121.75380775216 }, "steps_from_proto": { "total": 5982.842503272846, "count": 6880106, "is_parallel": true, "self": 687.3655153654108, "children": { "_process_rank_one_or_two_observation": { "total": 5295.476987907436, "count": 27520424, "is_parallel": true, "self": 5295.476987907436 } } } } } } } } } } }, "trainer_advance": { "total": 46180.42247313598, "count": 3440053, "self": 304.13181693355, "children": { "process_trajectory": { "total": 10740.988145737854, "count": 3440053, "self": 10732.491251361733, "children": { "RLTrainer._checkpoint": { "total": 8.496894376120963, "count": 100, "self": 8.496894376120963 } } }, "_update_policy": { "total": 35135.30251046458, "count": 2423, "self": 4493.156177746507, "children": { "TorchPOCAOptimizer.update": { "total": 30642.14633271807, "count": 72693, "self": 30642.14633271807 } } } } } } }, "trainer_threads": { "total": 3.3300602808594704e-07, "count": 1, "self": 3.3300602808594704e-07 }, "TrainerController._save_models": { "total": 0.0766474159900099, "count": 1, "self": 0.002105915977153927, "children": { "RLTrainer._checkpoint": { "total": 0.07454150001285598, "count": 1, "self": 0.07454150001285598 } } } } } } }