ppo-Huggy / run_logs /timers.json
MarBar's picture
Huggy
645c558
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066636562347412,
"min": 1.4066636562347412,
"max": 1.4278708696365356,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68310.3984375,
"min": 68310.3984375,
"max": 77624.1015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.62422997946612,
"min": 86.8804920913884,
"max": 421.11764705882354,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49004.0,
"min": 49004.0,
"max": 50113.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999370.0,
"min": 49517.0,
"max": 1999370.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999370.0,
"min": 49517.0,
"max": 1999370.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.400179862976074,
"min": 0.015623846091330051,
"max": 2.4562532901763916,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1168.8875732421875,
"min": 1.843613862991333,
"max": 1337.9716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.767382130363394,
"min": 1.9212695321036597,
"max": 3.922660370630429,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1834.7150974869728,
"min": 226.70980478823185,
"max": 2110.6977130770683,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.767382130363394,
"min": 1.9212695321036597,
"max": 3.922660370630429,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1834.7150974869728,
"min": 226.70980478823185,
"max": 2110.6977130770683,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019097566075571296,
"min": 0.013310882757650688,
"max": 0.020135662892425896,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05729269822671389,
"min": 0.026621765515301377,
"max": 0.05729269822671389,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0517172611422009,
"min": 0.022470193170011043,
"max": 0.058102391908566156,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15515178342660269,
"min": 0.044940386340022086,
"max": 0.16217593488593895,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.219798926766658e-06,
"min": 3.219798926766658e-06,
"max": 0.0002953092015635999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.659396780299975e-06,
"min": 9.659396780299975e-06,
"max": 0.00084396676867775,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107323333333335,
"min": 0.10107323333333335,
"max": 0.19843640000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30321970000000004,
"min": 0.20733744999999998,
"max": 0.5813222500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.35543433333332e-05,
"min": 6.35543433333332e-05,
"max": 0.00492197636,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019066302999999957,
"min": 0.00019066302999999957,
"max": 0.014067980275000003,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697938206",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697940634"
},
"total": 2428.110914708,
"count": 1,
"self": 0.42479354099987177,
"children": {
"run_training.setup": {
"total": 0.04534931900002448,
"count": 1,
"self": 0.04534931900002448
},
"TrainerController.start_learning": {
"total": 2427.640771848,
"count": 1,
"self": 4.5076770111386395,
"children": {
"TrainerController._reset_env": {
"total": 8.850594381000008,
"count": 1,
"self": 8.850594381000008
},
"TrainerController.advance": {
"total": 2414.1771020488613,
"count": 231882,
"self": 4.518625897901984,
"children": {
"env_step": {
"total": 1908.5828503299665,
"count": 231882,
"self": 1572.5934827720905,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.0497063500036,
"count": 231882,
"self": 16.96011298198289,
"children": {
"TorchPolicy.evaluate": {
"total": 316.0895933680207,
"count": 222891,
"self": 316.0895933680207
}
}
},
"workers": {
"total": 2.939661207872348,
"count": 231882,
"self": 0.0,
"children": {
"worker_root": {
"total": 2420.2255799000627,
"count": 231882,
"is_parallel": true,
"self": 1134.8478827871074,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008558110000080887,
"count": 1,
"is_parallel": true,
"self": 0.00027366399996253676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000582147000045552,
"count": 2,
"is_parallel": true,
"self": 0.000582147000045552
}
}
},
"UnityEnvironment.step": {
"total": 0.033321348000015405,
"count": 1,
"is_parallel": true,
"self": 0.0002902179999182408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021269800004120043,
"count": 1,
"is_parallel": true,
"self": 0.00021269800004120043
},
"communicator.exchange": {
"total": 0.03209062900003801,
"count": 1,
"is_parallel": true,
"self": 0.03209062900003801
},
"steps_from_proto": {
"total": 0.000727803000017957,
"count": 1,
"is_parallel": true,
"self": 0.00023354600006086912,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004942569999570878,
"count": 2,
"is_parallel": true,
"self": 0.0004942569999570878
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1285.3776971129553,
"count": 231881,
"is_parallel": true,
"self": 40.39914038392817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.79240431100214,
"count": 231881,
"is_parallel": true,
"self": 83.79240431100214
},
"communicator.exchange": {
"total": 1070.310188392989,
"count": 231881,
"is_parallel": true,
"self": 1070.310188392989
},
"steps_from_proto": {
"total": 90.8759640250359,
"count": 231881,
"is_parallel": true,
"self": 32.16683005292447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.70913397211143,
"count": 463762,
"is_parallel": true,
"self": 58.70913397211143
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.07562582099297,
"count": 231882,
"self": 6.686893032131536,
"children": {
"process_trajectory": {
"total": 148.87962504686215,
"count": 231882,
"self": 147.7675499118631,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1120751349990314,
"count": 10,
"self": 1.1120751349990314
}
}
},
"_update_policy": {
"total": 345.5091077419993,
"count": 97,
"self": 283.42942107999687,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.079686662002416,
"count": 2910,
"self": 62.079686662002416
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0349999683967326e-06,
"count": 1,
"self": 1.0349999683967326e-06
},
"TrainerController._save_models": {
"total": 0.10539737199997035,
"count": 1,
"self": 0.004019421000066359,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10137795099990399,
"count": 1,
"self": 0.10137795099990399
}
}
}
}
}
}
}