poca-SoccerTwos / run_logs /timers.json
Galeros's picture
First Push
e858d13
raw
history blame
20.2 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.5933685302734375,
"min": 1.555415391921997,
"max": 3.2957260608673096,
"count": 1190
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 31867.37109375,
"min": 7245.72607421875,
"max": 160250.546875,
"count": 1190
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 50.56701030927835,
"min": 39.86290322580645,
"max": 999.0,
"count": 1190
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19620.0,
"min": 1324.0,
"max": 29924.0,
"count": 1190
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1552.4123372657316,
"min": 1171.0870379635965,
"max": 1593.7937115535658,
"count": 1172
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 301167.99342955195,
"min": 2342.549064692899,
"max": 379277.177015662,
"count": 1172
},
"SoccerTwos.Step.mean": {
"value": 11899988.0,
"min": 9908.0,
"max": 11899988.0,
"count": 1190
},
"SoccerTwos.Step.sum": {
"value": 11899988.0,
"min": 9908.0,
"max": 11899988.0,
"count": 1190
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.05609159916639328,
"min": -0.10269837826490402,
"max": 0.1604011207818985,
"count": 1190
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -10.881770133972168,
"min": -20.803024291992188,
"max": 26.55428695678711,
"count": 1190
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05540889501571655,
"min": -0.10428468883037567,
"max": 0.16165974736213684,
"count": 1190
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -10.7493257522583,
"min": -20.830650329589844,
"max": 25.814809799194336,
"count": 1190
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1190
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1190
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.22509896847390637,
"min": -0.7,
"max": 0.43244597521321526,
"count": 1190
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -43.669199883937836,
"min": -67.99799966812134,
"max": 49.72719997167587,
"count": 1190
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.22509896847390637,
"min": -0.7,
"max": 0.43244597521321526,
"count": 1190
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -43.669199883937836,
"min": -67.99799966812134,
"max": 49.72719997167587,
"count": 1190
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1190
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1190
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.018065108659599597,
"min": 0.009599036445918804,
"max": 0.024713016274229935,
"count": 572
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.018065108659599597,
"min": 0.009599036445918804,
"max": 0.024713016274229935,
"count": 572
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10961750323573748,
"min": 5.087670245605598e-05,
"max": 0.1267578721046448,
"count": 572
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10961750323573748,
"min": 5.087670245605598e-05,
"max": 0.1267578721046448,
"count": 572
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.11107018887996674,
"min": 4.992426869042295e-05,
"max": 0.12836463153362274,
"count": 572
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.11107018887996674,
"min": 4.992426869042295e-05,
"max": 0.12836463153362274,
"count": 572
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 572
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 572
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.19999999999999996,
"max": 0.20000000000000007,
"count": 572
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.19999999999999996,
"max": 0.20000000000000007,
"count": 572
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 572
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 572
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681368361",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/agarcia/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "1681391743"
},
"total": 23381.772990735,
"count": 1,
"self": 0.25354983799843467,
"children": {
"run_training.setup": {
"total": 0.007767745000364812,
"count": 1,
"self": 0.007767745000364812
},
"TrainerController.start_learning": {
"total": 23381.511673152003,
"count": 1,
"self": 20.547621270012314,
"children": {
"TrainerController._reset_env": {
"total": 4.133485494004617,
"count": 60,
"self": 4.133485494004617
},
"TrainerController.advance": {
"total": 23356.09298498699,
"count": 816806,
"self": 20.105895319626143,
"children": {
"env_step": {
"total": 17012.01835669991,
"count": 816806,
"self": 13377.597879131725,
"children": {
"SubprocessEnvManager._take_step": {
"total": 3621.965414975484,
"count": 816806,
"self": 107.18239118388192,
"children": {
"TorchPolicy.evaluate": {
"total": 3514.783023791602,
"count": 1503958,
"self": 3514.783023791602
}
}
},
"workers": {
"total": 12.455062592702689,
"count": 816805,
"self": 0.0,
"children": {
"worker_root": {
"total": 23353.504601857137,
"count": 816805,
"is_parallel": true,
"self": 12172.06109010599,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002013325000007171,
"count": 2,
"is_parallel": true,
"self": 0.0005329470000106085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014803779999965627,
"count": 8,
"is_parallel": true,
"self": 0.0014803779999965627
}
}
},
"UnityEnvironment.step": {
"total": 0.023350181999830966,
"count": 1,
"is_parallel": true,
"self": 0.00044781700080420705,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003764809998756391,
"count": 1,
"is_parallel": true,
"self": 0.0003764809998756391
},
"communicator.exchange": {
"total": 0.021061302999896725,
"count": 1,
"is_parallel": true,
"self": 0.021061302999896725
},
"steps_from_proto": {
"total": 0.0014645809992543946,
"count": 2,
"is_parallel": true,
"self": 0.00030255999945438816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011620209998000064,
"count": 8,
"is_parallel": true,
"self": 0.0011620209998000064
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 11181.315135833142,
"count": 816804,
"is_parallel": true,
"self": 555.8757341502806,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 354.9397385261914,
"count": 816804,
"is_parallel": true,
"self": 354.9397385261914
},
"communicator.exchange": {
"total": 8646.955241935066,
"count": 816804,
"is_parallel": true,
"self": 8646.955241935066
},
"steps_from_proto": {
"total": 1623.5444212216044,
"count": 1633608,
"is_parallel": true,
"self": 324.40628953083296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1299.1381316907714,
"count": 6534432,
"is_parallel": true,
"self": 1299.1381316907714
}
}
}
}
},
"steps_from_proto": {
"total": 0.12837591800553128,
"count": 118,
"is_parallel": true,
"self": 0.02598310997518638,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.1023928080303449,
"count": 472,
"is_parallel": true,
"self": 0.1023928080303449
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 6323.968732967453,
"count": 816805,
"self": 130.42697614090685,
"children": {
"process_trajectory": {
"total": 2013.9432173255736,
"count": 816805,
"self": 2009.0746457905789,
"children": {
"RLTrainer._checkpoint": {
"total": 4.868571534994771,
"count": 23,
"self": 4.868571534994771
}
}
},
"_update_policy": {
"total": 4179.598539500973,
"count": 572,
"self": 1904.0242409148877,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2275.574298586085,
"count": 17172,
"self": 2275.574298586085
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.318998202914372e-06,
"count": 1,
"self": 6.318998202914372e-06
},
"TrainerController._save_models": {
"total": 0.737575081999239,
"count": 1,
"self": 0.0052373040016391315,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7323377779975999,
"count": 1,
"self": 0.7323377779975999
}
}
}
}
}
}
}