ppo-Huggy / run_logs /timers.json
ashkid's picture
Huggy
2b07479 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060250520706177,
"min": 1.4060250520706177,
"max": 1.4268009662628174,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70841.1640625,
"min": 68491.234375,
"max": 78558.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.98859315589354,
"min": 84.32136752136752,
"max": 399.544,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49438.0,
"min": 49119.0,
"max": 50016.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49773.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49773.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4135780334472656,
"min": 0.051320403814315796,
"max": 2.454935073852539,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1269.5419921875,
"min": 6.363729953765869,
"max": 1382.820556640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7770782347641063,
"min": 1.8162022320733917,
"max": 3.982747617789677,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1986.74315148592,
"min": 225.20907677710056,
"max": 2144.3513939380646,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7770782347641063,
"min": 1.8162022320733917,
"max": 3.982747617789677,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1986.74315148592,
"min": 225.20907677710056,
"max": 2144.3513939380646,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017502348428630892,
"min": 0.01459958907798864,
"max": 0.020302090403209957,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05250704528589267,
"min": 0.029207809565317197,
"max": 0.060906271209629874,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04990171318252881,
"min": 0.022357762791216373,
"max": 0.06113883884002765,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14970513954758644,
"min": 0.04471552558243275,
"max": 0.1828967353949944,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5665488111833316e-06,
"min": 3.5665488111833316e-06,
"max": 0.00029538000154000004,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0699646433549995e-05,
"min": 1.0699646433549995e-05,
"max": 0.0008443029185657001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118881666666667,
"min": 0.10118881666666667,
"max": 0.19845999999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30356645,
"min": 0.20753630000000003,
"max": 0.5814343000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.932195166666664e-05,
"min": 6.932195166666664e-05,
"max": 0.004923153999999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002079658549999999,
"min": 0.0002079658549999999,
"max": 0.014073571569999999,
"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": "1739707754",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739710227"
},
"total": 2472.7372166289997,
"count": 1,
"self": 0.43687488099931215,
"children": {
"run_training.setup": {
"total": 0.02275971999995363,
"count": 1,
"self": 0.02275971999995363
},
"TrainerController.start_learning": {
"total": 2472.2775820280003,
"count": 1,
"self": 4.472540797056354,
"children": {
"TrainerController._reset_env": {
"total": 3.2405448529999603,
"count": 1,
"self": 3.2405448529999603
},
"TrainerController.advance": {
"total": 2464.441184199944,
"count": 231985,
"self": 4.569920626978728,
"children": {
"env_step": {
"total": 1985.2691436869404,
"count": 231985,
"self": 1558.8032158680462,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.65173811286616,
"count": 231985,
"self": 15.86919229688965,
"children": {
"TorchPolicy.evaluate": {
"total": 407.7825458159765,
"count": 223004,
"self": 407.7825458159765
}
}
},
"workers": {
"total": 2.814189706027946,
"count": 231985,
"self": 0.0,
"children": {
"worker_root": {
"total": 2464.6075291580114,
"count": 231985,
"is_parallel": true,
"self": 1195.760277882016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010574269999779062,
"count": 1,
"is_parallel": true,
"self": 0.00026180800000474846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007956189999731578,
"count": 2,
"is_parallel": true,
"self": 0.0007956189999731578
}
}
},
"UnityEnvironment.step": {
"total": 0.06460716699996283,
"count": 1,
"is_parallel": true,
"self": 0.0003409239999427882,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000194125999996686,
"count": 1,
"is_parallel": true,
"self": 0.000194125999996686
},
"communicator.exchange": {
"total": 0.06330595600002198,
"count": 1,
"is_parallel": true,
"self": 0.06330595600002198
},
"steps_from_proto": {
"total": 0.0007661610000013752,
"count": 1,
"is_parallel": true,
"self": 0.00026377999995474966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005023810000466256,
"count": 2,
"is_parallel": true,
"self": 0.0005023810000466256
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1268.8472512759954,
"count": 231984,
"is_parallel": true,
"self": 37.67551730084028,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.50930588810127,
"count": 231984,
"is_parallel": true,
"self": 82.50930588810127
},
"communicator.exchange": {
"total": 1060.1079624551305,
"count": 231984,
"is_parallel": true,
"self": 1060.1079624551305
},
"steps_from_proto": {
"total": 88.55446563192322,
"count": 231984,
"is_parallel": true,
"self": 32.19546223078714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.35900340113608,
"count": 463968,
"is_parallel": true,
"self": 56.35900340113608
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.60211988602464,
"count": 231985,
"self": 6.70912806401725,
"children": {
"process_trajectory": {
"total": 164.00455445400712,
"count": 231985,
"self": 162.75639647700723,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2481579769998916,
"count": 10,
"self": 1.2481579769998916
}
}
},
"_update_policy": {
"total": 303.88843736800027,
"count": 97,
"self": 239.41443538900876,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.47400197899151,
"count": 2910,
"self": 64.47400197899151
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0839999049494509e-06,
"count": 1,
"self": 1.0839999049494509e-06
},
"TrainerController._save_models": {
"total": 0.12331109400020068,
"count": 1,
"self": 0.0021531720003622468,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12115792199983844,
"count": 1,
"self": 0.12115792199983844
}
}
}
}
}
}
}