| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.8453119993209839, | |
| "min": 1.7959303855895996, | |
| "max": 3.1746597290039062, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 35607.140625, | |
| "min": 31575.82421875, | |
| "max": 104805.4609375, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 52.75268817204301, | |
| "min": 40.3, | |
| "max": 835.2222222222222, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19624.0, | |
| "min": 12420.0, | |
| "max": 30068.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1534.1487276424448, | |
| "min": 1208.11384076554, | |
| "max": 1576.4673426757945, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 285351.66334149474, | |
| "min": 4838.015662397678, | |
| "max": 373729.15926845575, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 19999985.0, | |
| "min": 10009094.0, | |
| "max": 19999985.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 19999985.0, | |
| "min": 10009094.0, | |
| "max": 19999985.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.012030546553432941, | |
| "min": -0.1390942931175232, | |
| "max": 0.15518160164356232, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -2.2497122287750244, | |
| "min": -26.14972686767578, | |
| "max": 27.311962127685547, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.011924397200345993, | |
| "min": -0.13905742764472961, | |
| "max": 0.14362381398677826, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -2.2298622131347656, | |
| "min": -26.14279556274414, | |
| "max": 26.571941375732422, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.062252405493017186, | |
| "min": -0.7222222222222222, | |
| "max": 0.4907578982804951, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -11.641199827194214, | |
| "min": -65.71560001373291, | |
| "max": 54.24279999732971, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.062252405493017186, | |
| "min": -0.7222222222222222, | |
| "max": 0.4907578982804951, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -11.641199827194214, | |
| "min": -65.71560001373291, | |
| "max": 54.24279999732971, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 1000 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.01606463215284748, | |
| "min": 0.011753906412923242, | |
| "max": 0.022391153337472738, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01606463215284748, | |
| "min": 0.011753906412923242, | |
| "max": 0.022391153337472738, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.11406447775661946, | |
| "min": 0.006699031785440942, | |
| "max": 0.12618268517156442, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.11406447775661946, | |
| "min": 0.006699031785440942, | |
| "max": 0.12618268517156442, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.11516707812746366, | |
| "min": 0.006735981434273223, | |
| "max": 0.12829353486498196, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.11516707812746366, | |
| "min": 0.006735981434273223, | |
| "max": 0.12829353486498196, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.00010000000000000003, | |
| "min": 0.00010000000000000003, | |
| "max": 0.00010000000000000003, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.00010000000000000003, | |
| "min": 0.00010000000000000003, | |
| "max": 0.00010000000000000003, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.19999999999999993, | |
| "min": 0.19999999999999993, | |
| "max": 0.19999999999999993, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.19999999999999993, | |
| "min": 0.19999999999999993, | |
| "max": 0.19999999999999993, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 243 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 243 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1675857682", | |
| "python_version": "3.9.16 (main, Feb 6 2023, 20:06:40) \n[GCC 9.3.0]", | |
| "command_line_arguments": "/usr/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", | |
| "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": "1675898361" | |
| }, | |
| "total": 40679.31344649999, | |
| "count": 1, | |
| "self": 0.37271939995116554, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.027413400006480515, | |
| "count": 1, | |
| "self": 0.027413400006480515 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 40678.91331370003, | |
| "count": 1, | |
| "self": 24.216537802974926, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.1113256996904965, | |
| "count": 41, | |
| "self": 2.1113256996904965 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 40651.897886597406, | |
| "count": 691530, | |
| "self": 24.806593368237372, | |
| "children": { | |
| "env_step": { | |
| "total": 21551.900901413057, | |
| "count": 691530, | |
| "self": 18448.080454487208, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 3089.7628681033966, | |
| "count": 691530, | |
| "self": 126.78576909864205, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 2962.9770990047546, | |
| "count": 1256624, | |
| "self": 2962.9770990047546 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 14.057578822452342, | |
| "count": 691530, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 40627.10059819347, | |
| "count": 691530, | |
| "is_parallel": true, | |
| "self": 24597.19926019016, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.004719599994132295, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0011856999772135168, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0035339000169187784, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0035339000169187784 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.033716000005370006, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000892100011697039, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00039239999023266137, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00039239999023266137 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.029419200000120327, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.029419200000120327 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0030123000033199787, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0006713000475428998, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.002340999955777079, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.002340999955777079 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.09074609985691495, | |
| "count": 80, | |
| "is_parallel": true, | |
| "self": 0.020046699151862413, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.07069940070505254, | |
| "count": 320, | |
| "is_parallel": true, | |
| "self": 0.07069940070505254 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 16029.810591903457, | |
| "count": 691529, | |
| "is_parallel": true, | |
| "self": 522.5017652928364, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 408.4109345123579, | |
| "count": 691529, | |
| "is_parallel": true, | |
| "self": 408.4109345123579 | |
| }, | |
| "communicator.exchange": { | |
| "total": 13519.665367202339, | |
| "count": 691529, | |
| "is_parallel": true, | |
| "self": 13519.665367202339 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1579.2325248959241, | |
| "count": 1383058, | |
| "is_parallel": true, | |
| "self": 349.2951960033388, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1229.9373288925854, | |
| "count": 5532232, | |
| "is_parallel": true, | |
| "self": 1229.9373288925854 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 19075.19039181611, | |
| "count": 691530, | |
| "self": 138.25011521737906, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 3361.202004698571, | |
| "count": 691530, | |
| "self": 3356.168722598697, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 5.033282099873759, | |
| "count": 20, | |
| "self": 5.033282099873759 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 15575.738271900162, | |
| "count": 243, | |
| "self": 1793.8985213955457, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 13781.839750504616, | |
| "count": 14580, | |
| "self": 13781.839750504616 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.5999539755284786e-06, | |
| "count": 1, | |
| "self": 1.5999539755284786e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.6875620000064373, | |
| "count": 1, | |
| "self": 0.0026515000499784946, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.6849104999564588, | |
| "count": 1, | |
| "self": 0.6849104999564588 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |