ppo-Huggy / run_logs /timers.json
zhoppy's picture
Huggy
3030226
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037638902664185,
"min": 1.4037638902664185,
"max": 1.4264565706253052,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70209.25,
"min": 66170.421875,
"max": 80935.75,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.68553459119497,
"min": 90.23175182481752,
"max": 403.9758064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49458.0,
"min": 48792.0,
"max": 50206.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999946.0,
"min": 49670.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999946.0,
"min": 49670.0,
"max": 1999946.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3140785694122314,
"min": 0.07612539082765579,
"max": 2.413409471511841,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1103.8154296875,
"min": 9.363423347473145,
"max": 1305.571044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.559978306918274,
"min": 1.7232678270921475,
"max": 3.859278837986779,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1698.1096524000168,
"min": 211.96194273233414,
"max": 2058.029006123543,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.559978306918274,
"min": 1.7232678270921475,
"max": 3.859278837986779,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1698.1096524000168,
"min": 211.96194273233414,
"max": 2058.029006123543,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018322584357398832,
"min": 0.012614032017881981,
"max": 0.02016512862464879,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05496775307219649,
"min": 0.025228064035763963,
"max": 0.0550844083695362,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048124582030706936,
"min": 0.021673575416207312,
"max": 0.06049851557860772,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1443737460921208,
"min": 0.043347150832414624,
"max": 0.1713164365539948,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.17659894116666e-06,
"min": 3.17659894116666e-06,
"max": 0.00029527350157549997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.52979682349998e-06,
"min": 9.52979682349998e-06,
"max": 0.0008437518187493999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105883333333336,
"min": 0.10105883333333336,
"max": 0.19842449999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30317650000000007,
"min": 0.20726004999999997,
"max": 0.5812506000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.283578333333323e-05,
"min": 6.283578333333323e-05,
"max": 0.0049213825500000015,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018850734999999972,
"min": 0.00018850734999999972,
"max": 0.014064404940000002,
"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": "1670949684",
"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": "1670952007"
},
"total": 2322.7765944949997,
"count": 1,
"self": 0.4445044269996288,
"children": {
"run_training.setup": {
"total": 0.1051736179999807,
"count": 1,
"self": 0.1051736179999807
},
"TrainerController.start_learning": {
"total": 2322.22691645,
"count": 1,
"self": 4.2262450260532205,
"children": {
"TrainerController._reset_env": {
"total": 10.185080887000026,
"count": 1,
"self": 10.185080887000026
},
"TrainerController.advance": {
"total": 2307.699781162947,
"count": 231813,
"self": 4.152411477924488,
"children": {
"env_step": {
"total": 1830.5765968599915,
"count": 231813,
"self": 1536.540916089983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 291.30928186798053,
"count": 231813,
"self": 15.068845511970267,
"children": {
"TorchPolicy.evaluate": {
"total": 276.24043635601026,
"count": 222998,
"self": 68.38399504613574,
"children": {
"TorchPolicy.sample_actions": {
"total": 207.85644130987453,
"count": 222998,
"self": 207.85644130987453
}
}
}
}
},
"workers": {
"total": 2.7263989020278814,
"count": 231813,
"self": 0.0,
"children": {
"worker_root": {
"total": 2313.892592270981,
"count": 231813,
"is_parallel": true,
"self": 1050.5478835558836,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00401183199994648,
"count": 1,
"is_parallel": true,
"self": 0.00045267999985298957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035591520000934906,
"count": 2,
"is_parallel": true,
"self": 0.0035591520000934906
}
}
},
"UnityEnvironment.step": {
"total": 0.030568112000082692,
"count": 1,
"is_parallel": true,
"self": 0.0002985840001201723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001999979999709467,
"count": 1,
"is_parallel": true,
"self": 0.0001999979999709467
},
"communicator.exchange": {
"total": 0.029233822000037435,
"count": 1,
"is_parallel": true,
"self": 0.029233822000037435
},
"steps_from_proto": {
"total": 0.0008357079999541384,
"count": 1,
"is_parallel": true,
"self": 0.00027952999994340644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005561780000107319,
"count": 2,
"is_parallel": true,
"self": 0.0005561780000107319
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.3447087150973,
"count": 231812,
"is_parallel": true,
"self": 35.38069883915273,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.2697222840236,
"count": 231812,
"is_parallel": true,
"self": 81.2697222840236
},
"communicator.exchange": {
"total": 1048.662081818985,
"count": 231812,
"is_parallel": true,
"self": 1048.662081818985
},
"steps_from_proto": {
"total": 98.0322057729361,
"count": 231812,
"is_parallel": true,
"self": 43.094861608940164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.93734416399593,
"count": 463624,
"is_parallel": true,
"self": 54.93734416399593
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.9707728250312,
"count": 231813,
"self": 6.371512102956785,
"children": {
"process_trajectory": {
"total": 150.9192297510757,
"count": 231813,
"self": 150.4325768250759,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48665292599980603,
"count": 4,
"self": 0.48665292599980603
}
}
},
"_update_policy": {
"total": 315.6800309709987,
"count": 97,
"self": 261.7637656880014,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.9162652829973,
"count": 2910,
"self": 53.9162652829973
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.509999472356867e-07,
"count": 1,
"self": 9.509999472356867e-07
},
"TrainerController._save_models": {
"total": 0.11580842299963479,
"count": 1,
"self": 0.0025225649997082655,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11328585799992652,
"count": 1,
"self": 0.11328585799992652
}
}
}
}
}
}
}