ppo-Huggy / run_logs /timers.json
Pratikrathod08's picture
Huggy
7f3e477 verified
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404456615447998,
"min": 1.404456615447998,
"max": 1.426229476928711,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70419.453125,
"min": 68867.5546875,
"max": 76744.609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.57165861513688,
"min": 78.4737678855326,
"max": 407.7642276422764,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49414.0,
"min": 48770.0,
"max": 50155.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999960.0,
"min": 49665.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999960.0,
"min": 49665.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.436152219772339,
"min": 0.06344898045063019,
"max": 2.4876797199249268,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1512.8505859375,
"min": 7.740776062011719,
"max": 1523.083251953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.799023532541094,
"min": 1.8690849124896722,
"max": 3.930601275339723,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2359.1936137080193,
"min": 228.02835932374,
"max": 2359.1936137080193,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.799023532541094,
"min": 1.8690849124896722,
"max": 3.930601275339723,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2359.1936137080193,
"min": 228.02835932374,
"max": 2359.1936137080193,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017435166201256732,
"min": 0.01458056153448221,
"max": 0.020791261975925103,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05230549860377019,
"min": 0.02916112306896442,
"max": 0.059431218289925404,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06026107408106327,
"min": 0.023514393561830122,
"max": 0.06026107408106327,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18078322224318982,
"min": 0.047028787123660244,
"max": 0.18078322224318982,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5441488186499978e-06,
"min": 3.5441488186499978e-06,
"max": 0.0002953135515621501,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0632446455949993e-05,
"min": 1.0632446455949993e-05,
"max": 0.0008439967686677499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118135000000002,
"min": 0.10118135000000002,
"max": 0.19843784999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354405000000007,
"min": 0.20751385000000006,
"max": 0.5813322500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.894936499999998e-05,
"min": 6.894936499999998e-05,
"max": 0.004922048714999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020684809499999995,
"min": 0.00020684809499999995,
"max": 0.014068479274999997,
"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": "1723998994",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724001454"
},
"total": 2460.083029996,
"count": 1,
"self": 0.4762180879997686,
"children": {
"run_training.setup": {
"total": 0.053625338999950145,
"count": 1,
"self": 0.053625338999950145
},
"TrainerController.start_learning": {
"total": 2459.553186569,
"count": 1,
"self": 4.387822814991068,
"children": {
"TrainerController._reset_env": {
"total": 3.2542999839999993,
"count": 1,
"self": 3.2542999839999993
},
"TrainerController.advance": {
"total": 2451.793149080009,
"count": 232509,
"self": 4.813195910855029,
"children": {
"env_step": {
"total": 1945.3680143710308,
"count": 232509,
"self": 1603.2629412660226,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.22637149500486,
"count": 232509,
"self": 17.02287773801322,
"children": {
"TorchPolicy.evaluate": {
"total": 322.20349375699163,
"count": 222938,
"self": 322.20349375699163
}
}
},
"workers": {
"total": 2.878701610003418,
"count": 232509,
"self": 0.0,
"children": {
"worker_root": {
"total": 2452.120864685074,
"count": 232509,
"is_parallel": true,
"self": 1156.38801464107,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009803889998920567,
"count": 1,
"is_parallel": true,
"self": 0.00027838399989832396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007020049999937328,
"count": 2,
"is_parallel": true,
"self": 0.0007020049999937328
}
}
},
"UnityEnvironment.step": {
"total": 0.029537081000057697,
"count": 1,
"is_parallel": true,
"self": 0.0003768600001876621,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001942429998962325,
"count": 1,
"is_parallel": true,
"self": 0.0001942429998962325
},
"communicator.exchange": {
"total": 0.028205709999951978,
"count": 1,
"is_parallel": true,
"self": 0.028205709999951978
},
"steps_from_proto": {
"total": 0.0007602680000218243,
"count": 1,
"is_parallel": true,
"self": 0.00019765300010021747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005626149999216068,
"count": 2,
"is_parallel": true,
"self": 0.0005626149999216068
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1295.7328500440042,
"count": 232508,
"is_parallel": true,
"self": 38.08414494400017,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.65195112893582,
"count": 232508,
"is_parallel": true,
"self": 82.65195112893582
},
"communicator.exchange": {
"total": 1083.5101349990591,
"count": 232508,
"is_parallel": true,
"self": 1083.5101349990591
},
"steps_from_proto": {
"total": 91.48661897200907,
"count": 232508,
"is_parallel": true,
"self": 34.1603870600178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.32623191199127,
"count": 465016,
"is_parallel": true,
"self": 57.32623191199127
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 501.6119387981229,
"count": 232509,
"self": 6.7292503500667635,
"children": {
"process_trajectory": {
"total": 160.93137658805858,
"count": 232509,
"self": 159.44973032505823,
"children": {
"RLTrainer._checkpoint": {
"total": 1.481646263000357,
"count": 10,
"self": 1.481646263000357
}
}
},
"_update_policy": {
"total": 333.95131185999753,
"count": 97,
"self": 269.95871728399754,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.99259457599999,
"count": 2910,
"self": 63.99259457599999
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.069999578059651e-07,
"count": 1,
"self": 9.069999578059651e-07
},
"TrainerController._save_models": {
"total": 0.11791378299994904,
"count": 1,
"self": 0.0021663160000571224,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11574746699989191,
"count": 1,
"self": 0.11574746699989191
}
}
}
}
}
}
}