{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.37229585647583, "min": 1.356644868850708, "max": 3.2956838607788086, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 24679.369140625, "min": 24106.6640625, "max": 127093.109375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.94871794871795, "min": 38.536, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 1488.0, "max": 31896.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1634.4972260320167, "min": 1192.5861837779885, "max": 1719.327431954243, "count": 4997 }, "SoccerTwos.Self-play.ELO.sum": { "value": 254981.5672609946, "min": 2397.945535540182, "max": 388526.83807022055, "count": 4997 }, "SoccerTwos.Step.mean": { "value": 49999936.0, "min": 9858.0, "max": 49999936.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999936.0, "min": 9858.0, "max": 49999936.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03524751216173172, "min": -0.1419283151626587, "max": 0.13715900480747223, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.498611927032471, "min": -27.3740177154541, "max": 30.860774993896484, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03419635444879532, "min": -0.1438683420419693, "max": 0.13981013000011444, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.334631443023682, "min": -28.098796844482422, "max": 31.457279205322266, "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": -0.05703589549431434, "min": -0.5631789470973768, "max": 0.5324867918806256, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.897599697113037, "min": -67.57160007953644, "max": 57.71280038356781, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05703589549431434, "min": -0.5631789470973768, "max": 0.5324867918806256, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.897599697113037, "min": -67.57160007953644, "max": 57.71280038356781, "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": 0.018004724662750958, "min": 0.01054110166466368, "max": 0.02588704846954594, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018004724662750958, "min": 0.01054110166466368, "max": 0.02588704846954594, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09986016849676768, "min": 0.0006819044734584168, "max": 0.12943872114022573, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09986016849676768, "min": 0.0006819044734584168, "max": 0.12943872114022573, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10056763912240664, "min": 0.0006829419187852181, "max": 0.13169152662158012, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10056763912240664, "min": 0.0006829419187852181, "max": 0.13169152662158012, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714225033", "python_version": "3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]", "command_line_arguments": "/home/c/miniconda3/envs/up/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./trained-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1", "numpy_version": "1.23.5", "end_time_seconds": "1714257075" }, "total": 32042.219644875266, "count": 1, "self": 0.1668749786913395, "children": { "run_training.setup": { "total": 0.009759558364748955, "count": 1, "self": 0.009759558364748955 }, "TrainerController.start_learning": { "total": 32042.04301033821, "count": 1, "self": 33.378361814655364, "children": { "TrainerController._reset_env": { "total": 2.8961273580789566, "count": 250, "self": 2.8961273580789566 }, "TrainerController.advance": { "total": 32005.692719846033, "count": 3446107, "self": 32.78416582196951, "children": { "env_step": { "total": 23995.466805511154, "count": 3446107, "self": 18154.09656541329, "children": { "SubprocessEnvManager._take_step": { "total": 5820.598215113394, "count": 3446107, "self": 223.79183790739626, "children": { "TorchPolicy.evaluate": { "total": 5596.806377205998, "count": 6279176, "self": 5596.806377205998 } } }, "workers": { "total": 20.7720249844715, "count": 3446107, "self": 0.0, "children": { "worker_root": { "total": 31990.585800303146, "count": 3446107, "is_parallel": true, "self": 17552.246522780508, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011001769453287125, "count": 2, "is_parallel": true, "self": 0.0002501634880900383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008500134572386742, "count": 8, "is_parallel": true, "self": 0.0008500134572386742 } } }, "UnityEnvironment.step": { "total": 0.01166412141174078, "count": 1, "is_parallel": true, "self": 0.00024144165217876434, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021494925022125244, "count": 1, "is_parallel": true, "self": 0.00021494925022125244 }, "communicator.exchange": { "total": 0.010524923913180828, "count": 1, "is_parallel": true, "self": 0.010524923913180828 }, "steps_from_proto": { "total": 0.000682806596159935, "count": 2, "is_parallel": true, "self": 0.00013625714927911758, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005465494468808174, "count": 8, "is_parallel": true, "self": 0.0005465494468808174 } } } } } } }, "UnityEnvironment.step": { "total": 14438.161071165465, "count": 3446106, "is_parallel": true, "self": 812.0409971578047, "children": { "UnityEnvironment._generate_step_input": { "total": 531.2291127564386, "count": 3446106, "is_parallel": true, "self": 531.2291127564386 }, "communicator.exchange": { "total": 10844.018346969038, "count": 3446106, "is_parallel": true, "self": 10844.018346969038 }, "steps_from_proto": { "total": 2250.8726142821833, "count": 6892212, "is_parallel": true, "self": 418.27949241828173, "children": { "_process_rank_one_or_two_observation": { "total": 1832.5931218639016, "count": 27568848, "is_parallel": true, "self": 1832.5931218639016 } } } } }, "steps_from_proto": { "total": 0.17820635717362165, "count": 498, "is_parallel": true, "self": 0.03396888542920351, "children": { "_process_rank_one_or_two_observation": { "total": 0.14423747174441814, "count": 1992, "is_parallel": true, "self": 0.14423747174441814 } } } } } } } } }, "trainer_advance": { "total": 7977.441748512909, "count": 3446107, "self": 301.2638487685472, "children": { "process_trajectory": { "total": 3493.1214481806383, "count": 3446107, "self": 3484.6526933172718, "children": { "RLTrainer._checkpoint": { "total": 8.468754863366485, "count": 100, "self": 8.468754863366485 } } }, "_update_policy": { "total": 4183.056451563723, "count": 2424, "self": 2655.9490358438343, "children": { "TorchPOCAOptimizer.update": { "total": 1527.107415719889, "count": 72732, "self": 1527.107415719889 } } } } } } }, "trainer_threads": { "total": 3.7997961044311523e-07, "count": 1, "self": 3.7997961044311523e-07 }, "TrainerController._save_models": { "total": 0.07580093946307898, "count": 1, "self": 0.0009878072887659073, "children": { "RLTrainer._checkpoint": { "total": 0.07481313217431307, "count": 1, "self": 0.07481313217431307 } } } } } } }