{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.307533025741577, "min": 2.307533025741577, "max": 3.295701742172241, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45781.45703125, "min": 16348.001953125, "max": 107780.3984375, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.55555555555556, "min": 47.41747572815534, "max": 999.0, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18648.0, "min": 16692.0, "max": 23948.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1450.8970232833933, "min": 1198.931713842262, "max": 1462.3359987395977, "count": 198 }, "SoccerTwos.Self-play.ELO.sum": { "value": 235045.31777190973, "min": 2404.477419571058, "max": 286527.4587735868, "count": 198 }, "SoccerTwos.Step.mean": { "value": 1999990.0, "min": 9998.0, "max": 1999990.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 1999990.0, "min": 9998.0, "max": 1999990.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03722770884633064, "min": -0.07136625796556473, "max": 0.18781158328056335, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.030888557434082, "min": -11.632699966430664, "max": 19.53240394592285, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.035194698721170425, "min": -0.07054449617862701, "max": 0.17647695541381836, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.701540946960449, "min": -11.49875259399414, "max": 18.35360336303711, "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": -0.16177530862666942, "min": -0.5347517194419071, "max": 0.5304096129078132, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -26.207599997520447, "min": -44.9700003862381, "max": 55.16259974241257, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16177530862666942, "min": -0.5347517194419071, "max": 0.5304096129078132, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -26.207599997520447, "min": -44.9700003862381, "max": 55.16259974241257, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018693920023118458, "min": 0.012543374454253353, "max": 0.02186436578388869, "count": 96 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018693920023118458, "min": 0.012543374454253353, "max": 0.02186436578388869, "count": 96 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1002560280263424, "min": 0.0022964858333580198, "max": 0.10743579690655072, "count": 96 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1002560280263424, "min": 0.0022964858333580198, "max": 0.10743579690655072, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1014141634106636, "min": 0.002313785251074781, "max": 0.10904582043488821, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1014141634106636, "min": 0.002313785251074781, "max": 0.10904582043488821, "count": 96 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 96 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 96 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 96 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 96 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 96 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 96 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724401380", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/ai24/miniconda3/envs/hfrl7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724403708" }, "total": 2327.9935854979994, "count": 1, "self": 0.16762781600118615, "children": { "run_training.setup": { "total": 0.010233298999082763, "count": 1, "self": 0.010233298999082763 }, "TrainerController.start_learning": { "total": 2327.815724382999, "count": 1, "self": 1.452581569461472, "children": { "TrainerController._reset_env": { "total": 1.234213148998606, "count": 14, "self": 1.234213148998606 }, "TrainerController.advance": { "total": 2325.0313145595373, "count": 135732, "self": 1.3759033780588652, "children": { "env_step": { "total": 1898.9211854298665, "count": 135732, "self": 1191.3522834903215, "children": { "SubprocessEnvManager._take_step": { "total": 706.6355211982664, "count": 135732, "self": 9.782920157484114, "children": { "TorchPolicy.evaluate": { "total": 696.8526010407822, "count": 253936, "self": 696.8526010407822 } } }, "workers": { "total": 0.9333807412785973, "count": 135732, "self": 0.0, "children": { "worker_root": { "total": 2324.5866881452966, "count": 135732, "is_parallel": true, "self": 1284.9388557016919, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015676800012442982, "count": 2, "is_parallel": true, "self": 0.0006105560005380539, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009571240007062443, "count": 8, "is_parallel": true, "self": 0.0009571240007062443 } } }, "UnityEnvironment.step": { "total": 0.014677770999696804, "count": 1, "is_parallel": true, "self": 0.0002704719972825842, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001934970005095238, "count": 1, "is_parallel": true, "self": 0.0001934970005095238 }, "communicator.exchange": { "total": 0.013495855000655865, "count": 1, "is_parallel": true, "self": 0.013495855000655865 }, "steps_from_proto": { "total": 0.0007179470012488309, "count": 2, "is_parallel": true, "self": 0.00014968599862186238, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005682610026269685, "count": 8, "is_parallel": true, "self": 0.0005682610026269685 } } } } } } }, "UnityEnvironment.step": { "total": 1039.6382544476055, "count": 135731, "is_parallel": true, "self": 32.022296717377685, "children": { "UnityEnvironment._generate_step_input": { "total": 19.758511124269717, "count": 135731, "is_parallel": true, "self": 19.758511124269717 }, "communicator.exchange": { "total": 901.0258305711704, "count": 135731, "is_parallel": true, "self": 901.0258305711704 }, "steps_from_proto": { "total": 86.83161603478766, "count": 271462, "is_parallel": true, "self": 17.1833065849587, "children": { "_process_rank_one_or_two_observation": { "total": 69.64830944982896, "count": 1085848, "is_parallel": true, "self": 69.64830944982896 } } } } }, "steps_from_proto": { "total": 0.009577995999279665, "count": 26, "is_parallel": true, "self": 0.001984607002668781, "children": { "_process_rank_one_or_two_observation": { "total": 0.007593388996610884, "count": 104, "is_parallel": true, "self": 0.007593388996610884 } } } } } } } } }, "trainer_advance": { "total": 424.73422575161203, "count": 135732, "self": 11.67938789940672, "children": { "process_trajectory": { "total": 220.90293864320665, "count": 135732, "self": 220.38989543920616, "children": { "RLTrainer._checkpoint": { "total": 0.5130432040004962, "count": 4, "self": 0.5130432040004962 } } }, "_update_policy": { "total": 192.15189920899866, "count": 96, "self": 100.72317268801817, "children": { "TorchPOCAOptimizer.update": { "total": 91.42872652098049, "count": 2880, "self": 91.42872652098049 } } } } } } }, "trainer_threads": { "total": 5.070014594821259e-07, "count": 1, "self": 5.070014594821259e-07 }, "TrainerController._save_models": { "total": 0.09761459800029115, "count": 1, "self": 0.0006807940008002333, "children": { "RLTrainer._checkpoint": { "total": 0.09693380399949092, "count": 1, "self": 0.09693380399949092 } } } } } } }