{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4756355285644531, "min": 1.2978237867355347, "max": 3.295745611190796, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31637.626953125, "min": 23235.044921875, "max": 116324.859375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 85.56896551724138, "min": 39.699186991869915, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19852.0, "min": 15140.0, "max": 27908.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1776.7649151177247, "min": 1198.2180567289765, "max": 1846.4434251951945, "count": 4987 }, "SoccerTwos.Self-play.ELO.sum": { "value": 206104.73015365607, "min": 2396.5509993320493, "max": 422802.5951249929, "count": 4987 }, "SoccerTwos.Step.mean": { "value": 49999926.0, "min": 9970.0, "max": 49999926.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999926.0, "min": 9970.0, "max": 49999926.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.018933746963739395, "min": -0.1372309774160385, "max": 0.1623445749282837, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.196314573287964, "min": -27.851730346679688, "max": 27.091503143310547, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01998467557132244, "min": -0.14969651401042938, "max": 0.16986478865146637, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.3182222843170166, "min": -30.38839340209961, "max": 26.94598960876465, "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": -0.01756551553463114, "min": -0.6153846153846154, "max": 0.5457272637974132, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.037599802017212, "min": -75.49440014362335, "max": 64.44439995288849, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.01756551553463114, "min": -0.6153846153846154, "max": 0.5457272637974132, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.037599802017212, "min": -75.49440014362335, "max": 64.44439995288849, "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": 0.013691785931587219, "min": 0.009495296816627767, "max": 0.025735475623514505, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013691785931587219, "min": 0.009495296816627767, "max": 0.025735475623514505, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07996175289154053, "min": 2.5397517856617923e-05, "max": 0.13317935988307, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07996175289154053, "min": 2.5397517856617923e-05, "max": 0.13317935988307, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08090781743327777, "min": 2.6957952832162847e-05, "max": 0.135737781226635, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08090781743327777, "min": 2.6957952832162847e-05, "max": 0.135737781226635, "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": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716763793", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn --force ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos-001 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0", "numpy_version": "1.23.5", "end_time_seconds": "1716935012" }, "total": 171219.27670237498, "count": 1, "self": 0.18242091697175056, "children": { "run_training.setup": { "total": 0.013269540999317542, "count": 1, "self": 0.013269540999317542 }, "TrainerController.start_learning": { "total": 171219.081011917, "count": 1, "self": 31.257770368101774, "children": { "TrainerController._reset_env": { "total": 12.590659799958303, "count": 250, "self": 12.590659799958303 }, "TrainerController.advance": { "total": 171175.13169974895, "count": 3444336, "self": 29.032848853355972, "children": { "env_step": { "total": 138124.10667970876, "count": 3444336, "self": 133096.7276505906, "children": { "SubprocessEnvManager._take_step": { "total": 5007.574257688111, "count": 3444336, "self": 150.42064816422862, "children": { "TorchPolicy.evaluate": { "total": 4857.153609523883, "count": 6282274, "self": 4857.153609523883 } } }, "workers": { "total": 19.80477143004464, "count": 3444336, "self": 0.0, "children": { "worker_root": { "total": 171165.84883158753, "count": 3444336, "is_parallel": true, "self": 42123.76268863637, "children": { "steps_from_proto": { "total": 0.3698663835039042, "count": 500, "is_parallel": true, "self": 0.04107995965750888, "children": { "_process_rank_one_or_two_observation": { "total": 0.32878642384639534, "count": 2000, "is_parallel": true, "self": 0.32878642384639534 } } }, "UnityEnvironment.step": { "total": 129041.71627656765, "count": 3444336, "is_parallel": true, "self": 357.02263938727265, "children": { "UnityEnvironment._generate_step_input": { "total": 2273.3610816853106, "count": 3444336, "is_parallel": true, "self": 2273.3610816853106 }, "communicator.exchange": { "total": 121752.08375839358, "count": 3444336, "is_parallel": true, "self": 121752.08375839358 }, "steps_from_proto": { "total": 4659.248797101498, "count": 6888672, "is_parallel": true, "self": 507.09123357024873, "children": { "_process_rank_one_or_two_observation": { "total": 4152.157563531249, "count": 27554688, "is_parallel": true, "self": 4152.157563531249 } } } } } } } } } } }, "trainer_advance": { "total": 33021.99217118684, "count": 3444336, "self": 252.24339973379392, "children": { "process_trajectory": { "total": 7260.486781825728, "count": 3444336, "self": 7250.712993118652, "children": { "RLTrainer._checkpoint": { "total": 9.773788707076164, "count": 100, "self": 9.773788707076164 } } }, "_update_policy": { "total": 25509.261989627314, "count": 2423, "self": 2962.7607473233365, "children": { "TorchPOCAOptimizer.update": { "total": 22546.501242303977, "count": 72690, "self": 22546.501242303977 } } } } } } }, "trainer_threads": { "total": 3.3300602808594704e-07, "count": 1, "self": 3.3300602808594704e-07 }, "TrainerController._save_models": { "total": 0.100881666992791, "count": 1, "self": 0.0005530419875867665, "children": { "RLTrainer._checkpoint": { "total": 0.10032862500520423, "count": 1, "self": 0.10032862500520423 } } } } } } }