poca-SoccerTwos / run_logs /timers.json
4mirfor3v3r's picture
First Push
270aa7c verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.2356741428375244,
"min": 3.2356741428375244,
"max": 3.2957539558410645,
"count": 24
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 70822.4375,
"min": 13165.1484375,
"max": 106859.71875,
"count": 24
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 725.625,
"min": 430.0,
"max": 999.0,
"count": 24
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 23220.0,
"min": 12752.0,
"max": 29344.0,
"count": 24
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1200.328350025257,
"min": 1196.084934587261,
"max": 1200.328350025257,
"count": 22
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 9602.626800202055,
"min": 2396.017105905693,
"max": 19158.17786114626,
"count": 22
},
"SoccerTwos.Step.mean": {
"value": 239652.0,
"min": 9702.0,
"max": 239652.0,
"count": 24
},
"SoccerTwos.Step.sum": {
"value": 239652.0,
"min": 9702.0,
"max": 239652.0,
"count": 24
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.010748249478638172,
"min": -0.015848787501454353,
"max": 0.0049892268143594265,
"count": 24
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.16122373938560486,
"min": -0.3018549680709839,
"max": 0.05574318766593933,
"count": 24
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.00980287604033947,
"min": -0.01843317598104477,
"max": 0.00641221646219492,
"count": 24
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.1470431387424469,
"min": -0.38591599464416504,
"max": 0.06412216275930405,
"count": 24
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 24
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 24
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.2916266699632009,
"min": -0.4049333333969116,
"max": 0.2916266699632009,
"count": 24
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 4.374400049448013,
"min": -6.074000000953674,
"max": 4.374400049448013,
"count": 24
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.2916266699632009,
"min": -0.4049333333969116,
"max": 0.2916266699632009,
"count": 24
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 4.374400049448013,
"min": -6.074000000953674,
"max": 4.374400049448013,
"count": 24
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 24
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 24
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.013738706193786735,
"min": 0.011652058274679196,
"max": 0.018887079992176346,
"count": 10
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.013738706193786735,
"min": 0.011652058274679196,
"max": 0.018887079992176346,
"count": 10
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.004847104948324462,
"min": 0.001309396008340021,
"max": 0.004847104948324462,
"count": 10
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.004847104948324462,
"min": 0.001309396008340021,
"max": 0.004847104948324462,
"count": 10
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.004941717876742284,
"min": 0.0013768509263172746,
"max": 0.004941717876742284,
"count": 10
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.004941717876742284,
"min": 0.0013768509263172746,
"max": 0.004941717876742284,
"count": 10
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 10
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 10
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 10
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 10
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 10
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1717155158",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SmartJenglot --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717156520"
},
"total": 1361.6774423420002,
"count": 1,
"self": 0.14953070800038404,
"children": {
"run_training.setup": {
"total": 0.07977151099976254,
"count": 1,
"self": 0.07977151099976254
},
"TrainerController.start_learning": {
"total": 1361.448140123,
"count": 1,
"self": 0.6261698330126819,
"children": {
"TrainerController._reset_env": {
"total": 3.9106206610003937,
"count": 2,
"self": 3.9106206610003937
},
"TrainerController.advance": {
"total": 1356.237072997987,
"count": 15954,
"self": 0.742367473016202,
"children": {
"env_step": {
"total": 572.6961661059881,
"count": 15954,
"self": 462.2354413899702,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.06870883000738,
"count": 15954,
"self": 4.007063854014177,
"children": {
"TorchPolicy.evaluate": {
"total": 106.0616449759932,
"count": 31708,
"self": 106.0616449759932
}
}
},
"workers": {
"total": 0.39201588601054027,
"count": 15954,
"self": 0.0,
"children": {
"worker_root": {
"total": 1358.2675042019996,
"count": 15954,
"is_parallel": true,
"self": 977.8814039430013,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009716647999994166,
"count": 2,
"is_parallel": true,
"self": 0.006128322001131892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003588325998862274,
"count": 8,
"is_parallel": true,
"self": 0.003588325998862274
}
}
},
"UnityEnvironment.step": {
"total": 0.04824683600008939,
"count": 1,
"is_parallel": true,
"self": 0.00151112900039152,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009825110000747372,
"count": 1,
"is_parallel": true,
"self": 0.0009825110000747372
},
"communicator.exchange": {
"total": 0.04112590599970645,
"count": 1,
"is_parallel": true,
"self": 0.04112590599970645
},
"steps_from_proto": {
"total": 0.004627289999916684,
"count": 2,
"is_parallel": true,
"self": 0.0009523969997644599,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003674893000152224,
"count": 8,
"is_parallel": true,
"self": 0.003674893000152224
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 380.38357752999855,
"count": 15953,
"is_parallel": true,
"self": 23.837662855981307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.915127958002358,
"count": 15953,
"is_parallel": true,
"self": 15.915127958002358
},
"communicator.exchange": {
"total": 268.7250908339988,
"count": 15953,
"is_parallel": true,
"self": 268.7250908339988
},
"steps_from_proto": {
"total": 71.90569588201606,
"count": 31906,
"is_parallel": true,
"self": 12.54011092004157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.36558496197449,
"count": 127624,
"is_parallel": true,
"self": 59.36558496197449
}
}
}
}
},
"steps_from_proto": {
"total": 0.0025227289997928892,
"count": 2,
"is_parallel": true,
"self": 0.0005233449992374517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019993840005554375,
"count": 8,
"is_parallel": true,
"self": 0.0019993840005554375
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 782.7985394189827,
"count": 15954,
"self": 4.602201102013623,
"children": {
"process_trajectory": {
"total": 99.18953993096966,
"count": 15954,
"self": 99.18953993096966
},
"_update_policy": {
"total": 679.0067983859994,
"count": 11,
"self": 52.32679753599405,
"children": {
"TorchPOCAOptimizer.update": {
"total": 626.6800008500054,
"count": 336,
"self": 626.6800008500054
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.717000031931093e-06,
"count": 1,
"self": 1.717000031931093e-06
},
"TrainerController._save_models": {
"total": 0.6742749139998523,
"count": 1,
"self": 0.0035950709998360253,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6706798430000163,
"count": 1,
"self": 0.6706798430000163
}
}
}
}
}
}
}