{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.15842604637146, "min": 3.1336007118225098, "max": 3.2957088947296143, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 67312.375, "min": 45246.9375, "max": 132625.390625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 884.3333333333334, "min": 236.71428571428572, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21224.0, "min": 6628.0, "max": 30148.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1215.659811500077, "min": 1200.2435735709535, "max": 1215.659811500077, "count": 48 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4862.639246000308, "min": 2400.487147141907, "max": 19407.802034341934, "count": 48 }, "SoccerTwos.Step.mean": { "value": 499660.0, "min": 9770.0, "max": 499660.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499660.0, "min": 9770.0, "max": 499660.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01406072173267603, "min": -0.04412545636296272, "max": 0.008145976811647415, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.16872866451740265, "min": -0.7728478908538818, "max": 0.14344337582588196, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012719911523163319, "min": -0.044171370565891266, "max": 0.009948012419044971, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.15263894200325012, "min": -0.7974553108215332, "max": 0.16911621391773224, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1884333292643229, "min": -0.42857142857142855, "max": 0.28112380845206125, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.261199951171875, "min": -6.481600046157837, "max": 5.914799869060516, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1884333292643229, "min": -0.42857142857142855, "max": 0.28112380845206125, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.261199951171875, "min": -6.481600046157837, "max": 5.914799869060516, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013158223312348127, "min": 0.013158223312348127, "max": 0.02181773379512985, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013158223312348127, "min": 0.013158223312348127, "max": 0.02181773379512985, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002371368452440947, "min": 0.001030550831152747, "max": 0.008068540676807364, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002371368452440947, "min": 0.001030550831152747, "max": 0.008068540676807364, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0023823169137661654, "min": 0.0010245292204975462, "max": 0.00846226663949589, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0023823169137661654, "min": 0.0010245292204975462, "max": 0.00846226663949589, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686155198", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/root/anaconda3/envs/minerl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwosSmall --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686157268" }, "total": 2070.2178055, "count": 1, "self": 1.0250520999998116, "children": { "run_training.setup": { "total": 0.00976950000006127, "count": 1, "self": 0.00976950000006127 }, "TrainerController.start_learning": { "total": 2069.1829839, "count": 1, "self": 1.3087680999606164, "children": { "TrainerController._reset_env": { "total": 24.69935509999982, "count": 24, "self": 24.69935509999982 }, "TrainerController.advance": { "total": 2042.8906650000397, "count": 41247, "self": 1.531998200058979, "children": { "env_step": { "total": 1800.0333814000205, "count": 41247, "self": 1292.097474000071, "children": { "SubprocessEnvManager._take_step": { "total": 507.09667869996053, "count": 41247, "self": 9.963009099907708, "children": { "TorchPolicy.evaluate": { "total": 497.1336696000528, "count": 81874, "self": 497.1336696000528 } } }, "workers": { "total": 0.8392286999890075, "count": 41247, "self": 0.0, "children": { "worker_root": { "total": 2064.7671305000245, "count": 41247, "is_parallel": true, "self": 913.0688027000447, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.021959499999979926, "count": 2, "is_parallel": true, "self": 0.019849999999905776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021095000000741493, "count": 8, "is_parallel": true, "self": 0.0021095000000741493 } } }, "UnityEnvironment.step": { "total": 0.04585650000001351, "count": 1, "is_parallel": true, "self": 0.000559800000019095, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010837999999466774, "count": 1, "is_parallel": true, "self": 0.0010837999999466774 }, "communicator.exchange": { "total": 0.0426003000000037, "count": 1, "is_parallel": true, "self": 0.0426003000000037 }, "steps_from_proto": { "total": 0.00161260000004404, "count": 2, "is_parallel": true, "self": 0.00036639999996168626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012462000000823537, "count": 8, "is_parallel": true, "self": 0.0012462000000823537 } } } } } } }, "UnityEnvironment.step": { "total": 1151.6590933999796, "count": 41246, "is_parallel": true, "self": 32.20160970006327, "children": { "UnityEnvironment._generate_step_input": { "total": 21.53810140003327, "count": 41246, "is_parallel": true, "self": 21.53810140003327 }, "communicator.exchange": { "total": 1000.0520061999762, "count": 41246, "is_parallel": true, "self": 1000.0520061999762 }, "steps_from_proto": { "total": 97.867376099907, "count": 82492, "is_parallel": true, "self": 20.509618399821647, "children": { "_process_rank_one_or_two_observation": { "total": 77.35775770008536, "count": 329968, "is_parallel": true, "self": 77.35775770008536 } } } } }, "steps_from_proto": { "total": 0.03923440000005485, "count": 46, "is_parallel": true, "self": 0.008302300002924312, "children": { "_process_rank_one_or_two_observation": { "total": 0.030932099997130535, "count": 184, "is_parallel": true, "self": 0.030932099997130535 } } } } } } } } }, "trainer_advance": { "total": 241.3252853999603, "count": 41247, "self": 6.886319299973252, "children": { "process_trajectory": { "total": 61.18131969998774, "count": 41247, "self": 60.558825599988154, "children": { "RLTrainer._checkpoint": { "total": 0.6224940999995852, "count": 1, "self": 0.6224940999995852 } } }, "_update_policy": { "total": 173.25764639999932, "count": 23, "self": 91.8774011999974, "children": { "TorchPOCAOptimizer.update": { "total": 81.38024520000192, "count": 699, "self": 81.38024520000192 } } } } } } }, "trainer_threads": { "total": 1.5999999050109182e-06, "count": 1, "self": 1.5999999050109182e-06 }, "TrainerController._save_models": { "total": 0.2841941000001498, "count": 1, "self": 0.001792300000488467, "children": { "RLTrainer._checkpoint": { "total": 0.2824017999996613, "count": 1, "self": 0.2824017999996613 } } } } } } }