{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.5629613399505615, "min": 1.090325951576233, "max": 3.2956714630126953, "count": 1320 }, "SoccerTwos.Policy.Entropy.sum": { "value": 59706.75, "min": 11362.4169921875, "max": 146715.15625, "count": 1320 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 388.3636363636364, "max": 999.0, "count": 1320 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 15408.0, "max": 27460.0, "count": 1320 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1195.897377664415, "min": 1195.147380779826, "max": 1206.6418633238047, "count": 151 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2391.79475532883, "min": 2390.294761559652, "max": 14442.18571063296, "count": 151 }, "SoccerTwos.Step.mean": { "value": 13199096.0, "min": 9746.0, "max": 13199096.0, "count": 1320 }, "SoccerTwos.Step.sum": { "value": 13199096.0, "min": 9746.0, "max": 13199096.0, "count": 1320 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0006780090043321252, "min": -0.0471428781747818, "max": 0.009688681922852993, "count": 1320 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.006780089810490608, "min": -0.5657145380973816, "max": 0.17439627647399902, "count": 1320 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0006756127113476396, "min": -0.048940613865852356, "max": 0.009682822972536087, "count": 1320 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.006756127346307039, "min": -0.5872873663902283, "max": 0.17429080605506897, "count": 1320 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1320 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1320 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5714285714285714, "max": 0.265857138804027, "count": 1320 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -12.0, "max": 3.721999943256378, "count": 1320 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5714285714285714, "max": 0.265857138804027, "count": 1320 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -12.0, "max": 3.721999943256378, "count": 1320 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1320 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1320 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014628700644243509, "min": 0.010528013772758034, "max": 0.024146205701011544, "count": 604 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014628700644243509, "min": 0.010528013772758034, "max": 0.024146205701011544, "count": 604 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 4.2402060344374585e-09, "min": 2.5057145363234964e-11, "max": 0.0049857560778036715, "count": 604 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 4.2402060344374585e-09, "min": 2.5057145363234964e-11, "max": 0.0049857560778036715, "count": 604 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 4.140490824274442e-09, "min": 3.5931467292268e-11, "max": 0.005010603795138498, "count": 604 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 4.140490824274442e-09, "min": 3.5931467292268e-11, "max": 0.005010603795138498, "count": 604 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 604 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 604 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 604 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 604 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 604 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 604 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686164536", "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=SoccerTwos --no-graphics", "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": "1686207818" }, "total": 43281.8585525, "count": 1, "self": 4.761372799999663, "children": { "run_training.setup": { "total": 0.014972599999964586, "count": 1, "self": 0.014972599999964586 }, "TrainerController.start_learning": { "total": 43277.0822071, "count": 1, "self": 26.601716397992277, "children": { "TrainerController._reset_env": { "total": 15.187777499997537, "count": 66, "self": 15.187777499997537 }, "TrainerController.advance": { "total": 43234.593672602015, "count": 859615, "self": 30.274263003084343, "children": { "env_step": { "total": 37339.720084800916, "count": 859615, "self": 27120.534577501134, "children": { "SubprocessEnvManager._take_step": { "total": 10201.970169599059, "count": 859615, "self": 194.18200579627046, "children": { "TorchPolicy.evaluate": { "total": 10007.788163802788, "count": 1708336, "self": 10007.788163802788 } } }, "workers": { "total": 17.215337700723467, "count": 859614, "self": 0.0, "children": { "worker_root": { "total": 43202.95499459556, "count": 859614, "is_parallel": true, "self": 18997.979871497, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006010900000546826, "count": 2, "is_parallel": true, "self": 0.0016422000044258311, "children": { "_process_rank_one_or_two_observation": { "total": 0.004368699996120995, "count": 8, "is_parallel": true, "self": 0.004368699996120995 } } }, "UnityEnvironment.step": { "total": 0.07845700000143552, "count": 1, "is_parallel": true, "self": 0.0009665000034146942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0018215999989479315, "count": 1, "is_parallel": true, "self": 0.0018215999989479315 }, "communicator.exchange": { "total": 0.07252589999916381, "count": 1, "is_parallel": true, "self": 0.07252589999916381 }, "steps_from_proto": { "total": 0.0031429999999090796, "count": 2, "is_parallel": true, "self": 0.0010912000016105594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020517999982985202, "count": 8, "is_parallel": true, "self": 0.0020517999982985202 } } } } } } }, "UnityEnvironment.step": { "total": 24204.86327149852, "count": 859613, "is_parallel": true, "self": 670.5529938022155, "children": { "UnityEnvironment._generate_step_input": { "total": 447.2874415982369, "count": 859613, "is_parallel": true, "self": 447.2874415982369 }, "communicator.exchange": { "total": 21050.30774079735, "count": 859613, "is_parallel": true, "self": 21050.30774079735 }, "steps_from_proto": { "total": 2036.7150953007167, "count": 1719226, "is_parallel": true, "self": 429.09325930625346, "children": { "_process_rank_one_or_two_observation": { "total": 1607.6218359944633, "count": 6876904, "is_parallel": true, "self": 1607.6218359944633 } } } } }, "steps_from_proto": { "total": 0.11185160003878991, "count": 130, "is_parallel": true, "self": 0.023299200052861124, "children": { "_process_rank_one_or_two_observation": { "total": 0.08855239998592879, "count": 520, "is_parallel": true, "self": 0.08855239998592879 } } } } } } } } }, "trainer_advance": { "total": 5864.599324798013, "count": 859614, "self": 161.7723587993969, "children": { "process_trajectory": { "total": 1412.6063274985827, "count": 859614, "self": 1402.7833817985756, "children": { "RLTrainer._checkpoint": { "total": 9.82294570000704, "count": 26, "self": 9.82294570000704 } } }, "_update_policy": { "total": 4290.220638500034, "count": 604, "self": 2265.2581233000456, "children": { "TorchPOCAOptimizer.update": { "total": 2024.962515199988, "count": 18120, "self": 2024.962515199988 } } } } } } }, "trainer_threads": { "total": 2.0000006770715117e-06, "count": 1, "self": 2.0000006770715117e-06 }, "TrainerController._save_models": { "total": 0.699038599996129, "count": 1, "self": 0.01795999999740161, "children": { "RLTrainer._checkpoint": { "total": 0.6810785999987274, "count": 1, "self": 0.6810785999987274 } } } } } } }