ppo-Huggy / run_logs /timers.json
hendoo's picture
Huggy
8be04ce
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4017144441604614,
"min": 1.4017144441604614,
"max": 1.4262889623641968,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69541.859375,
"min": 68909.0625,
"max": 76503.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.20813771517997,
"min": 75.99536321483771,
"max": 427.6837606837607,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49336.0,
"min": 49067.0,
"max": 50082.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999255.0,
"min": 49548.0,
"max": 1999255.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999255.0,
"min": 49548.0,
"max": 1999255.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4697272777557373,
"min": 0.02379610203206539,
"max": 2.5557892322540283,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1578.15576171875,
"min": 2.760347843170166,
"max": 1597.3682861328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.838771642467039,
"min": 1.8536602897119934,
"max": 3.995501280498505,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2452.975079536438,
"min": 215.02459360659122,
"max": 2497.1883003115654,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.838771642467039,
"min": 1.8536602897119934,
"max": 3.995501280498505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2452.975079536438,
"min": 215.02459360659122,
"max": 2497.1883003115654,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016755610991660636,
"min": 0.013754393726897737,
"max": 0.01960904617505245,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050266832974981905,
"min": 0.027508787453795473,
"max": 0.05637657660263358,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06406285357144144,
"min": 0.022605646463731924,
"max": 0.06808679749568303,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1921885607143243,
"min": 0.04521129292746385,
"max": 0.19269170425832272,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6227487924499943e-06,
"min": 3.6227487924499943e-06,
"max": 0.00029530650156449996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0868246377349983e-05,
"min": 1.0868246377349983e-05,
"max": 0.0008440146186618001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120755000000003,
"min": 0.10120755000000003,
"max": 0.19843550000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036226500000001,
"min": 0.20757389999999998,
"max": 0.5813382,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.02567449999999e-05,
"min": 7.02567449999999e-05,
"max": 0.00492193145,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002107702349999997,
"min": 0.0002107702349999997,
"max": 0.014068776179999999,
"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": "1670962777",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1670965017"
},
"total": 2239.8545586309997,
"count": 1,
"self": 0.40342203999944104,
"children": {
"run_training.setup": {
"total": 0.10186949299998105,
"count": 1,
"self": 0.10186949299998105
},
"TrainerController.start_learning": {
"total": 2239.3492670980004,
"count": 1,
"self": 3.993927428875395,
"children": {
"TrainerController._reset_env": {
"total": 9.936139594999986,
"count": 1,
"self": 9.936139594999986
},
"TrainerController.advance": {
"total": 2225.3028517161256,
"count": 232705,
"self": 4.006003613144458,
"children": {
"env_step": {
"total": 1761.140566156998,
"count": 232705,
"self": 1474.1577607248623,
"children": {
"SubprocessEnvManager._take_step": {
"total": 284.36042301509747,
"count": 232705,
"self": 14.648986665155121,
"children": {
"TorchPolicy.evaluate": {
"total": 269.71143634994235,
"count": 222846,
"self": 67.59942410197038,
"children": {
"TorchPolicy.sample_actions": {
"total": 202.11201224797196,
"count": 222846,
"self": 202.11201224797196
}
}
}
}
},
"workers": {
"total": 2.622382417038125,
"count": 232705,
"self": 0.0,
"children": {
"worker_root": {
"total": 2231.3612182670363,
"count": 232705,
"is_parallel": true,
"self": 1018.9926401280254,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017242210000176783,
"count": 1,
"is_parallel": true,
"self": 0.00032192000014674704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014023009998709313,
"count": 2,
"is_parallel": true,
"self": 0.0014023009998709313
}
}
},
"UnityEnvironment.step": {
"total": 0.029555173000062496,
"count": 1,
"is_parallel": true,
"self": 0.0002795220001416965,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022138799999993353,
"count": 1,
"is_parallel": true,
"self": 0.00022138799999993353
},
"communicator.exchange": {
"total": 0.02832206599998699,
"count": 1,
"is_parallel": true,
"self": 0.02832206599998699
},
"steps_from_proto": {
"total": 0.0007321969999338762,
"count": 1,
"is_parallel": true,
"self": 0.00026289400000223395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00046930299993164226,
"count": 2,
"is_parallel": true,
"self": 0.00046930299993164226
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1212.3685781390109,
"count": 232704,
"is_parallel": true,
"self": 34.737933241107385,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.45638758293671,
"count": 232704,
"is_parallel": true,
"self": 78.45638758293671
},
"communicator.exchange": {
"total": 1003.9436801210131,
"count": 232704,
"is_parallel": true,
"self": 1003.9436801210131
},
"steps_from_proto": {
"total": 95.23057719395376,
"count": 232704,
"is_parallel": true,
"self": 41.67913586598263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.55144132797113,
"count": 465408,
"is_parallel": true,
"self": 53.55144132797113
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 460.1562819459832,
"count": 232705,
"self": 5.851347327097415,
"children": {
"process_trajectory": {
"total": 150.801434488886,
"count": 232705,
"self": 150.29702322188598,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5044112670000231,
"count": 4,
"self": 0.5044112670000231
}
}
},
"_update_policy": {
"total": 303.5035001299998,
"count": 97,
"self": 250.921330492008,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.5821696379918,
"count": 2910,
"self": 52.5821696379918
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.019997039809823e-07,
"count": 1,
"self": 8.019997039809823e-07
},
"TrainerController._save_models": {
"total": 0.11634755599970958,
"count": 1,
"self": 0.002057269999568234,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11429028600014135,
"count": 1,
"self": 0.11429028600014135
}
}
}
}
}
}
}