ppo-Huggy / run_logs /timers.json
RajMoodley's picture
Huggy
c9610ae
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.412573218345642,
"min": 1.412573218345642,
"max": 1.427993655204773,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69632.796875,
"min": 68226.2578125,
"max": 78159.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.42833333333333,
"min": 80.21044045676999,
"max": 375.6865671641791,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49457.0,
"min": 48828.0,
"max": 50342.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49858.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49858.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.413515329360962,
"min": 0.02923383191227913,
"max": 2.489234447479248,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1448.1092529296875,
"min": 3.8880996704101562,
"max": 1495.2470703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.749555952946345,
"min": 1.7047560752782607,
"max": 3.931232291084903,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2249.733571767807,
"min": 226.73255801200867,
"max": 2328.216257750988,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.749555952946345,
"min": 1.7047560752782607,
"max": 3.931232291084903,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2249.733571767807,
"min": 226.73255801200867,
"max": 2328.216257750988,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016611883840717684,
"min": 0.01199751026482166,
"max": 0.02111938595068447,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04983565152215305,
"min": 0.02399502052964332,
"max": 0.057674094604832735,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05845824310349094,
"min": 0.02215937850996852,
"max": 0.06428798741350572,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17537472931047282,
"min": 0.04431875701993704,
"max": 0.17547147360940774,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6050987983333355e-06,
"min": 3.6050987983333355e-06,
"max": 0.00029531527656157495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0815296395000007e-05,
"min": 1.0815296395000007e-05,
"max": 0.0008439673686775499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120166666666669,
"min": 0.10120166666666669,
"max": 0.19843842500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30360500000000007,
"min": 0.20753044999999998,
"max": 0.58132245,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.996316666666672e-05,
"min": 6.996316666666672e-05,
"max": 0.004922077407500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020988950000000017,
"min": 0.00020988950000000017,
"max": 0.014067990254999998,
"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": "1670776682",
"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": "1670779081"
},
"total": 2399.324045409,
"count": 1,
"self": 0.3874520859999393,
"children": {
"run_training.setup": {
"total": 0.10592571099994075,
"count": 1,
"self": 0.10592571099994075
},
"TrainerController.start_learning": {
"total": 2398.830667612,
"count": 1,
"self": 4.205447059916423,
"children": {
"TrainerController._reset_env": {
"total": 10.647814202999939,
"count": 1,
"self": 10.647814202999939
},
"TrainerController.advance": {
"total": 2383.858912553084,
"count": 232081,
"self": 4.405093435123035,
"children": {
"env_step": {
"total": 1892.0098667679572,
"count": 232081,
"self": 1585.8437316910076,
"children": {
"SubprocessEnvManager._take_step": {
"total": 303.2443011800318,
"count": 232081,
"self": 15.880047200038803,
"children": {
"TorchPolicy.evaluate": {
"total": 287.364253979993,
"count": 222888,
"self": 70.84062773399546,
"children": {
"TorchPolicy.sample_actions": {
"total": 216.52362624599755,
"count": 222888,
"self": 216.52362624599755
}
}
}
}
},
"workers": {
"total": 2.9218338969177466,
"count": 232081,
"self": 0.0,
"children": {
"worker_root": {
"total": 2389.997869574046,
"count": 232081,
"is_parallel": true,
"self": 1090.7992875730547,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018506769999930839,
"count": 1,
"is_parallel": true,
"self": 0.00033431300005304365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015163639999400402,
"count": 2,
"is_parallel": true,
"self": 0.0015163639999400402
}
}
},
"UnityEnvironment.step": {
"total": 0.033243313000070884,
"count": 1,
"is_parallel": true,
"self": 0.0003163049999557188,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019621100000222214,
"count": 1,
"is_parallel": true,
"self": 0.00019621100000222214
},
"communicator.exchange": {
"total": 0.031877665000024535,
"count": 1,
"is_parallel": true,
"self": 0.031877665000024535
},
"steps_from_proto": {
"total": 0.000853132000088408,
"count": 1,
"is_parallel": true,
"self": 0.00030513299998347065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005479990001049373,
"count": 2,
"is_parallel": true,
"self": 0.0005479990001049373
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.1985820009913,
"count": 232080,
"is_parallel": true,
"self": 36.73674470092783,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.86782391902068,
"count": 232080,
"is_parallel": true,
"self": 84.86782391902068
},
"communicator.exchange": {
"total": 1077.2346689040542,
"count": 232080,
"is_parallel": true,
"self": 1077.2346689040542
},
"steps_from_proto": {
"total": 100.35934447698855,
"count": 232080,
"is_parallel": true,
"self": 43.87145302485487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.48789145213368,
"count": 464160,
"is_parallel": true,
"self": 56.48789145213368
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.4439523500034,
"count": 232081,
"self": 6.5736163999984,
"children": {
"process_trajectory": {
"total": 157.92381352600376,
"count": 232081,
"self": 157.42971500700367,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49409851900009016,
"count": 4,
"self": 0.49409851900009016
}
}
},
"_update_policy": {
"total": 322.9465224240013,
"count": 97,
"self": 269.0780713710052,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.86845105299608,
"count": 2910,
"self": 53.86845105299608
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.005999820336001e-06,
"count": 1,
"self": 1.005999820336001e-06
},
"TrainerController._save_models": {
"total": 0.1184927899998911,
"count": 1,
"self": 0.0020343039996078005,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1164584860002833,
"count": 1,
"self": 0.1164584860002833
}
}
}
}
}
}
}