eolang's picture
17320000steps 28478.773 seconds
190c4d6
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.6945322751998901,
"min": 1.6440521478652954,
"max": 3.2957375049591064,
"count": 1732
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 34378.671875,
"min": 9812.767578125,
"max": 135094.953125,
"count": 1732
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 53.91208791208791,
"min": 40.8,
"max": 999.0,
"count": 1732
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19624.0,
"min": 11200.0,
"max": 29912.0,
"count": 1732
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1571.1724978762136,
"min": 1181.89900171139,
"max": 1627.487197510313,
"count": 1103
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 285953.3946134709,
"min": 2364.775553328018,
"max": 379906.98697277356,
"count": 1103
},
"SoccerTwos.Step.mean": {
"value": 17319904.0,
"min": 9974.0,
"max": 17319904.0,
"count": 1732
},
"SoccerTwos.Step.sum": {
"value": 17319904.0,
"min": 9974.0,
"max": 17319904.0,
"count": 1732
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.011440613307058811,
"min": -0.13983193039894104,
"max": 0.145553857088089,
"count": 1732
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -2.093632221221924,
"min": -25.868907928466797,
"max": 20.857337951660156,
"count": 1732
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.009945583529770374,
"min": -0.13742756843566895,
"max": 0.14491654932498932,
"count": 1732
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.8200417757034302,
"min": -25.424100875854492,
"max": 22.011672973632812,
"count": 1732
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1732
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1732
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.012077595692514723,
"min": -0.6070514304297311,
"max": 0.4821600009554199,
"count": 1732
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 2.210200011730194,
"min": -69.42079997062683,
"max": 65.43320000171661,
"count": 1732
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.012077595692514723,
"min": -0.6070514304297311,
"max": 0.4821600009554199,
"count": 1732
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 2.210200011730194,
"min": -69.42079997062683,
"max": 65.43320000171661,
"count": 1732
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1732
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1732
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.013892653519481732,
"min": 0.009432440353945519,
"max": 0.02377440301546206,
"count": 818
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.013892653519481732,
"min": 0.009432440353945519,
"max": 0.02377440301546206,
"count": 818
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09296852300564448,
"min": 1.0835932780691356e-09,
"max": 0.11838824426134427,
"count": 818
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09296852300564448,
"min": 1.0835932780691356e-09,
"max": 0.11838824426134427,
"count": 818
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09445213824510575,
"min": 1.5502604718461062e-09,
"max": 0.11982380747795104,
"count": 818
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09445213824510575,
"min": 1.5502604718461062e-09,
"max": 0.11982380747795104,
"count": 818
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 818
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 818
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 818
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 818
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 818
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 818
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678359308",
"python_version": "3.9.16 (main, Mar 1 2023, 18:22:10) \n[GCC 11.2.0]",
"command_line_arguments": "/home/ara/miniconda3/envs/drl/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": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1678387796"
},
"total": 28488.760613606995,
"count": 1,
"self": 0.05016930599595071,
"children": {
"run_training.setup": {
"total": 0.01153841899940744,
"count": 1,
"self": 0.01153841899940744
},
"TrainerController.start_learning": {
"total": 28488.698905882,
"count": 1,
"self": 26.385146121920116,
"children": {
"TrainerController._reset_env": {
"total": 7.13303097899734,
"count": 87,
"self": 7.13303097899734
},
"TrainerController.advance": {
"total": 28454.85967897508,
"count": 1155258,
"self": 25.546761182391492,
"children": {
"env_step": {
"total": 19594.5517629542,
"count": 1155258,
"self": 14152.911318714532,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5425.8014616786695,
"count": 1155258,
"self": 148.41389325343516,
"children": {
"TorchPolicy.evaluate": {
"total": 5277.387568425234,
"count": 2204835,
"self": 5277.387568425234
}
}
},
"workers": {
"total": 15.838982560999284,
"count": 1155257,
"self": 0.0,
"children": {
"worker_root": {
"total": 28442.97017423469,
"count": 1155257,
"is_parallel": true,
"self": 17193.55133210963,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00252888199975132,
"count": 2,
"is_parallel": true,
"self": 0.0005944869972154265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019343950025358936,
"count": 8,
"is_parallel": true,
"self": 0.0019343950025358936
}
}
},
"UnityEnvironment.step": {
"total": 0.021791152999867336,
"count": 1,
"is_parallel": true,
"self": 0.0005187219994695624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042961100007232744,
"count": 1,
"is_parallel": true,
"self": 0.00042961100007232744
},
"communicator.exchange": {
"total": 0.019247747999543208,
"count": 1,
"is_parallel": true,
"self": 0.019247747999543208
},
"steps_from_proto": {
"total": 0.0015950720007822383,
"count": 2,
"is_parallel": true,
"self": 0.0003363780033396324,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001258693997442606,
"count": 8,
"is_parallel": true,
"self": 0.001258693997442606
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 11249.272867153031,
"count": 1155256,
"is_parallel": true,
"self": 624.9351420071216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 457.5448579443146,
"count": 1155256,
"is_parallel": true,
"self": 457.5448579443146
},
"communicator.exchange": {
"total": 8337.200181680797,
"count": 1155256,
"is_parallel": true,
"self": 8337.200181680797
},
"steps_from_proto": {
"total": 1829.592685520798,
"count": 2310512,
"is_parallel": true,
"self": 390.7295801955006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1438.8631053252975,
"count": 9242048,
"is_parallel": true,
"self": 1438.8631053252975
}
}
}
}
},
"steps_from_proto": {
"total": 0.1459749720288528,
"count": 172,
"is_parallel": true,
"self": 0.03321641205184278,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.11275855997701001,
"count": 688,
"is_parallel": true,
"self": 0.11275855997701001
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 8834.761154838488,
"count": 1155257,
"self": 200.49638543481524,
"children": {
"process_trajectory": {
"total": 2306.2318827496747,
"count": 1155257,
"self": 2295.597574744679,
"children": {
"RLTrainer._checkpoint": {
"total": 10.634308004995546,
"count": 34,
"self": 10.634308004995546
}
}
},
"_update_policy": {
"total": 6328.0328866539985,
"count": 818,
"self": 2641.8031753411833,
"children": {
"TorchPOCAOptimizer.update": {
"total": 3686.229711312815,
"count": 24543,
"self": 3686.229711312815
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.369978215545416e-07,
"count": 1,
"self": 9.369978215545416e-07
},
"TrainerController._save_models": {
"total": 0.32104886900197016,
"count": 1,
"self": 0.0018547900035628118,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31919407899840735,
"count": 1,
"self": 0.31919407899840735
}
}
}
}
}
}
}