SoccerTwos / run_logs /timers.json
akanametov's picture
Trained SoccerTwos agent upload
215c71f
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.763279676437378,
"min": 1.7627720832824707,
"max": 3.2957794666290283,
"count": 501
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 38933.21484375,
"min": 5362.5556640625,
"max": 123490.8671875,
"count": 501
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 54.84090909090909,
"min": 49.70103092783505,
"max": 999.0,
"count": 501
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19304.0,
"min": 9800.0,
"max": 31508.0,
"count": 501
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1728.190525683003,
"min": 1198.623129271598,
"max": 1729.5992784306775,
"count": 496
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 304161.5325202085,
"min": 2398.5014391117093,
"max": 325557.13011846866,
"count": 496
},
"SoccerTwos.Step.mean": {
"value": 5009990.0,
"min": 9770.0,
"max": 5009990.0,
"count": 501
},
"SoccerTwos.Step.sum": {
"value": 5009990.0,
"min": 9770.0,
"max": 5009990.0,
"count": 501
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.010855700820684433,
"min": -0.08616485446691513,
"max": 0.22946183383464813,
"count": 501
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.910603404045105,
"min": -13.1670560836792,
"max": 28.32492446899414,
"count": 501
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.01102946326136589,
"min": -0.09055808931589127,
"max": 0.23681262135505676,
"count": 501
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.941185474395752,
"min": -13.221481323242188,
"max": 28.46109390258789,
"count": 501
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 501
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 501
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.05359318005767735,
"min": -0.6842105263157895,
"max": 0.5431671254847148,
"count": 501
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -9.432399690151215,
"min": -49.87540024518967,
"max": 60.46240025758743,
"count": 501
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.05359318005767735,
"min": -0.6842105263157895,
"max": 0.5431671254847148,
"count": 501
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -9.432399690151215,
"min": -49.87540024518967,
"max": 60.46240025758743,
"count": 501
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 501
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 501
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.018286445655394345,
"min": 0.011096207809168845,
"max": 0.02578775945585221,
"count": 241
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.018286445655394345,
"min": 0.011096207809168845,
"max": 0.02578775945585221,
"count": 241
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09370836615562439,
"min": 0.0001470294587003688,
"max": 0.11192481741309165,
"count": 241
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09370836615562439,
"min": 0.0001470294587003688,
"max": 0.11192481741309165,
"count": 241
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09523454234004021,
"min": 0.00014546279829422322,
"max": 0.11390603135029474,
"count": 241
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09523454234004021,
"min": 0.00014546279829422322,
"max": 0.11390603135029474,
"count": 241
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 241
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 241
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 241
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 241
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 241
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 241
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675507806",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675518503"
},
"total": 10696.952395657001,
"count": 1,
"self": 0.008657954000227619,
"children": {
"run_training.setup": {
"total": 0.10492984199981947,
"count": 1,
"self": 0.10492984199981947
},
"TrainerController.start_learning": {
"total": 10696.838807861,
"count": 1,
"self": 7.637551484531286,
"children": {
"TrainerController._reset_env": {
"total": 7.208755112001654,
"count": 21,
"self": 7.208755112001654
},
"TrainerController.advance": {
"total": 10681.705715357468,
"count": 339372,
"self": 8.2085601897561,
"children": {
"env_step": {
"total": 8173.161437269959,
"count": 339372,
"self": 6389.692351913645,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1778.7781281045477,
"count": 339372,
"self": 52.32697369944299,
"children": {
"TorchPolicy.evaluate": {
"total": 1726.4511544051047,
"count": 630082,
"self": 342.87420412475603,
"children": {
"TorchPolicy.sample_actions": {
"total": 1383.5769502803487,
"count": 630082,
"self": 1383.5769502803487
}
}
}
}
},
"workers": {
"total": 4.690957251765667,
"count": 339372,
"self": 0.0,
"children": {
"worker_root": {
"total": 10676.10815116707,
"count": 339372,
"is_parallel": true,
"self": 5273.880832516912,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002955854999981966,
"count": 2,
"is_parallel": true,
"self": 0.0010334649996366352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001922390000345331,
"count": 8,
"is_parallel": true,
"self": 0.001922390000345331
}
}
},
"UnityEnvironment.step": {
"total": 0.046050422999996954,
"count": 1,
"is_parallel": true,
"self": 0.0009331419992122392,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007787910003571596,
"count": 1,
"is_parallel": true,
"self": 0.0007787910003571596
},
"communicator.exchange": {
"total": 0.04104007600017212,
"count": 1,
"is_parallel": true,
"self": 0.04104007600017212
},
"steps_from_proto": {
"total": 0.003298414000255434,
"count": 2,
"is_parallel": true,
"self": 0.00072860899990701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002569805000348424,
"count": 8,
"is_parallel": true,
"self": 0.002569805000348424
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 5402.18682615416,
"count": 339371,
"is_parallel": true,
"self": 294.2810369544104,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 218.92566442502448,
"count": 339371,
"is_parallel": true,
"self": 218.92566442502448
},
"communicator.exchange": {
"total": 3863.215772637293,
"count": 339371,
"is_parallel": true,
"self": 3863.215772637293
},
"steps_from_proto": {
"total": 1025.7643521374325,
"count": 678742,
"is_parallel": true,
"self": 211.2246886271646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 814.5396635102679,
"count": 2714968,
"is_parallel": true,
"self": 814.5396635102679
}
}
}
}
},
"steps_from_proto": {
"total": 0.040492495998023514,
"count": 40,
"is_parallel": true,
"self": 0.009093962000861211,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0313985339971623,
"count": 160,
"is_parallel": true,
"self": 0.0313985339971623
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2500.3357178977526,
"count": 339371,
"self": 51.16921958570083,
"children": {
"process_trajectory": {
"total": 1088.809994030044,
"count": 339371,
"self": 1086.5901447440424,
"children": {
"RLTrainer._checkpoint": {
"total": 2.2198492860015904,
"count": 10,
"self": 2.2198492860015904
}
}
},
"_update_policy": {
"total": 1360.3565042820078,
"count": 241,
"self": 823.9206043540098,
"children": {
"TorchPOCAOptimizer.update": {
"total": 536.435899927998,
"count": 7230,
"self": 536.435899927998
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.835000148275867e-06,
"count": 1,
"self": 1.835000148275867e-06
},
"TrainerController._save_models": {
"total": 0.28678407199913636,
"count": 1,
"self": 0.0024939939994510496,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2842900779996853,
"count": 1,
"self": 0.2842900779996853
}
}
}
}
}
}
}