archbold's picture
First Push
79b6ecb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.7668840885162354,
"min": 2.766847610473633,
"max": 2.890342950820923,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4078.38720703125,
"min": 1898.29052734375,
"max": 4273.15478515625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 960.0,
"max": 19992.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 960.0,
"max": 19992.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.527904987335205,
"min": 0.03839648887515068,
"max": 1.527904987335205,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 39.725528717041016,
"min": 0.5759473443031311,
"max": 39.725528717041016,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 9
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 2189.0,
"min": 2189.0,
"max": 2189.0,
"count": 9
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06979520766831496,
"min": 0.05810726352844059,
"max": 0.07497810010396529,
"count": 9
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06979520766831496,
"min": 0.05810726352844059,
"max": 0.07497810010396529,
"count": 9
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2400400308417339,
"min": 0.07358381004693608,
"max": 0.2400400308417339,
"count": 9
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.2400400308417339,
"min": 0.07358381004693608,
"max": 0.2400400308417339,
"count": 9
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.320098559999991e-06,
"min": 4.320098559999991e-06,
"max": 0.00026832001056,
"count": 9
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.320098559999991e-06,
"min": 4.320098559999991e-06,
"max": 0.00026832001056,
"count": 9
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10144,
"min": 0.10144,
"max": 0.18944000000000003,
"count": 9
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10144,
"min": 0.10144,
"max": 0.18944000000000003,
"count": 9
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.185599999999986e-05,
"min": 8.185599999999986e-05,
"max": 0.0044730559999999996,
"count": 9
},
"SnowballTarget.Policy.Beta.sum": {
"value": 8.185599999999986e-05,
"min": 8.185599999999986e-05,
"max": 0.0044730559999999996,
"count": 9
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 5.363636363636363,
"min": 2.0,
"max": 5.636363636363637,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 59.0,
"min": 2.0,
"max": 62.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 5.363636363636363,
"min": 2.0,
"max": 5.636363636363637,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 59.0,
"min": 2.0,
"max": 62.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714794799",
"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/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714794853"
},
"total": 54.032786837,
"count": 1,
"self": 0.4781430209998234,
"children": {
"run_training.setup": {
"total": 0.05568767500017202,
"count": 1,
"self": 0.05568767500017202
},
"TrainerController.start_learning": {
"total": 53.49895614100001,
"count": 1,
"self": 0.09775012499949298,
"children": {
"TrainerController._reset_env": {
"total": 3.010872395999968,
"count": 1,
"self": 3.010872395999968
},
"TrainerController.advance": {
"total": 50.29246225100064,
"count": 1870,
"self": 0.03213204899930133,
"children": {
"env_step": {
"total": 50.26033020200134,
"count": 1870,
"self": 31.83221448299696,
"children": {
"SubprocessEnvManager._take_step": {
"total": 18.395608803003142,
"count": 1870,
"self": 0.16581403100576608,
"children": {
"TorchPolicy.evaluate": {
"total": 18.229794771997376,
"count": 1870,
"self": 18.229794771997376
}
}
},
"workers": {
"total": 0.032506916001239006,
"count": 1870,
"self": 0.0,
"children": {
"worker_root": {
"total": 53.263518744994826,
"count": 1870,
"is_parallel": true,
"self": 28.37821806899342,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006396518999963519,
"count": 1,
"is_parallel": true,
"self": 0.004694955999639205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017015630003243132,
"count": 10,
"is_parallel": true,
"self": 0.0017015630003243132
}
}
},
"UnityEnvironment.step": {
"total": 0.06937331700009963,
"count": 1,
"is_parallel": true,
"self": 0.0007105290001163667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004322970000885107,
"count": 1,
"is_parallel": true,
"self": 0.0004322970000885107
},
"communicator.exchange": {
"total": 0.0661038399998688,
"count": 1,
"is_parallel": true,
"self": 0.0661038399998688
},
"steps_from_proto": {
"total": 0.0021266510000259586,
"count": 1,
"is_parallel": true,
"self": 0.0004142540001339512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017123969998920074,
"count": 10,
"is_parallel": true,
"self": 0.0017123969998920074
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 24.885300676001407,
"count": 1869,
"is_parallel": true,
"self": 1.1356849860151215,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.5893852269953186,
"count": 1869,
"is_parallel": true,
"self": 0.5893852269953186
},
"communicator.exchange": {
"total": 19.48167329299349,
"count": 1869,
"is_parallel": true,
"self": 19.48167329299349
},
"steps_from_proto": {
"total": 3.6785571699974753,
"count": 1869,
"is_parallel": true,
"self": 0.7408858369824429,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.9376713330150324,
"count": 18690,
"is_parallel": true,
"self": 2.9376713330150324
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00032976099987536145,
"count": 1,
"self": 0.00032976099987536145,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 49.712023435010224,
"count": 78761,
"is_parallel": true,
"self": 1.5397172339771714,
"children": {
"process_trajectory": {
"total": 28.287863149033683,
"count": 78761,
"is_parallel": true,
"self": 27.698589726033788,
"children": {
"RLTrainer._checkpoint": {
"total": 0.589273422999895,
"count": 4,
"is_parallel": true,
"self": 0.589273422999895
}
}
},
"_update_policy": {
"total": 19.88444305199937,
"count": 9,
"is_parallel": true,
"self": 4.8609458239998276,
"children": {
"TorchPPOOptimizer.update": {
"total": 15.023497227999542,
"count": 456,
"is_parallel": true,
"self": 15.023497227999542
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09754160800002865,
"count": 1,
"self": 0.0010328299999855517,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0965087780000431,
"count": 1,
"self": 0.0965087780000431
}
}
}
}
}
}
}