{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3793267011642456, "min": 1.3793267011642456, "max": 3.2957565784454346, "count": 2931 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27718.94921875, "min": 24510.728515625, "max": 111241.546875, "count": 2931 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.5, "min": 43.88392857142857, "max": 999.0, "count": 2931 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19688.0, "min": 11108.0, "max": 29124.0, "count": 2931 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1777.3672927016828, "min": 1187.1355443554899, "max": 1809.638853821049, "count": 2924 }, "SoccerTwos.Self-play.ELO.sum": { "value": 327035.5818571096, "min": 2376.4458394388193, "max": 391389.74313705164, "count": 2924 }, "SoccerTwos.Step.mean": { "value": 29309748.0, "min": 9578.0, "max": 29309748.0, "count": 2931 }, "SoccerTwos.Step.sum": { "value": 29309748.0, "min": 9578.0, "max": 29309748.0, "count": 2931 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04328304901719093, "min": -0.12975358963012695, "max": 0.2650556266307831, "count": 2931 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.964080810546875, "min": -20.2652587890625, "max": 42.14384460449219, "count": 2931 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03899843618273735, "min": -0.12693586945533752, "max": 0.26724952459335327, "count": 2931 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.1757121086120605, "min": -19.973880767822266, "max": 42.49267578125, "count": 2931 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2931 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2931 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.09998260827168175, "min": -0.7058823529411765, "max": 0.6306411772966385, "count": 2931 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 18.39679992198944, "min": -72.00539976358414, "max": 86.3988002538681, "count": 2931 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.09998260827168175, "min": -0.7058823529411765, "max": 0.6306411772966385, "count": 2931 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 18.39679992198944, "min": -72.00539976358414, "max": 86.3988002538681, "count": 2931 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2931 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2931 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020598530618008225, "min": 0.010126874673490723, "max": 0.02589762446716198, "count": 1418 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020598530618008225, "min": 0.010126874673490723, "max": 0.02589762446716198, "count": 1418 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10980251083771388, "min": 0.0002885118396079633, "max": 0.11844818890094758, "count": 1418 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10980251083771388, "min": 0.0002885118396079633, "max": 0.11844818890094758, "count": 1418 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1127667320271333, "min": 0.0002903129245775441, "max": 0.1221135770281156, "count": 1418 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1127667320271333, "min": 0.0002903129245775441, "max": 0.1221135770281156, "count": 1418 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1418 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1418 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1418 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1418 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1418 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1418 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685132439", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/ikari/miniconda3/envs/rl_soccer/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "2.0.1", "numpy_version": "1.19.5", "end_time_seconds": "1685203290" }, "total": 70851.01857193, "count": 1, "self": 0.07782156392931938, "children": { "run_training.setup": { "total": 0.011746842414140701, "count": 1, "self": 0.011746842414140701 }, "TrainerController.start_learning": { "total": 70850.92900352366, "count": 1, "self": 29.933638103306293, "children": { "TrainerController._reset_env": { "total": 7.19331438280642, "count": 147, "self": 7.19331438280642 }, "TrainerController.advance": { "total": 70813.5616074428, "count": 2002519, "self": 30.801735682412982, "children": { "env_step": { "total": 60917.53753804043, "count": 2002519, "self": 55136.82301384024, "children": { "SubprocessEnvManager._take_step": { "total": 5763.484326103702, "count": 2002519, "self": 197.60012598894536, "children": { "TorchPolicy.evaluate": { "total": 5565.884200114757, "count": 3684440, "self": 5565.884200114757 } } }, "workers": { "total": 17.230198096483946, "count": 2002519, "self": 0.0, "children": { "worker_root": { "total": 70727.3711008057, "count": 2002519, "is_parallel": true, "self": 20347.01834078133, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007606273517012596, "count": 2, "is_parallel": true, "self": 0.0010822713375091553, "children": { "_process_rank_one_or_two_observation": { "total": 0.006524002179503441, "count": 8, "is_parallel": true, "self": 0.006524002179503441 } } }, "UnityEnvironment.step": { "total": 0.044678887352347374, "count": 1, "is_parallel": true, "self": 0.0018883123993873596, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010650809854269028, "count": 1, "is_parallel": true, "self": 0.0010650809854269028 }, "communicator.exchange": { "total": 0.03491946496069431, "count": 1, "is_parallel": true, "self": 0.03491946496069431 }, "steps_from_proto": { "total": 0.0068060290068387985, "count": 2, "is_parallel": true, "self": 0.0007760580629110336, "children": { "_process_rank_one_or_two_observation": { "total": 0.006029970943927765, "count": 8, "is_parallel": true, "self": 0.006029970943927765 } } } } } } }, "UnityEnvironment.step": { "total": 50379.30705574155, "count": 2002518, "is_parallel": true, "self": 3052.1572255827487, "children": { "UnityEnvironment._generate_step_input": { "total": 1597.6672714110464, "count": 2002518, "is_parallel": true, "self": 1597.6672714110464 }, "communicator.exchange": { "total": 32271.85264592804, "count": 2002518, "is_parallel": true, "self": 32271.85264592804 }, "steps_from_proto": { "total": 13457.629912819713, "count": 4005036, "is_parallel": true, "self": 1453.1702462658286, "children": { "_process_rank_one_or_two_observation": { "total": 12004.459666553885, "count": 16020144, "is_parallel": true, "self": 12004.459666553885 } } } } }, "steps_from_proto": { "total": 1.0457042828202248, "count": 292, "is_parallel": true, "self": 0.11493476666510105, "children": { "_process_rank_one_or_two_observation": { "total": 0.9307695161551237, "count": 1168, "is_parallel": true, "self": 0.9307695161551237 } } } } } } } } }, "trainer_advance": { "total": 9865.222333719954, "count": 2002519, "self": 291.25986043550074, "children": { "process_trajectory": { "total": 3459.344151297584, "count": 2002519, "self": 3445.628598632291, "children": { "RLTrainer._checkpoint": { "total": 13.715552665293217, "count": 58, "self": 13.715552665293217 } } }, "_update_policy": { "total": 6114.618321986869, "count": 1419, "self": 3864.2482283804566, "children": { "TorchPOCAOptimizer.update": { "total": 2250.3700936064124, "count": 42554, "self": 2250.3700936064124 } } } } } } }, "trainer_threads": { "total": 1.3746321201324463e-06, "count": 1, "self": 1.3746321201324463e-06 }, "TrainerController._save_models": { "total": 0.24044222012162209, "count": 1, "self": 0.0014268383383750916, "children": { "RLTrainer._checkpoint": { "total": 0.239015381783247, "count": 1, "self": 0.239015381783247 } } } } } } }