ppo-Huggy / run_logs /timers.json
DipakBundheliya's picture
Huggy project created
2de785f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024643898010254,
"min": 1.4024643898010254,
"max": 1.4285889863967896,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71097.9296875,
"min": 68777.5390625,
"max": 77949.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.60336906584992,
"min": 72.06286549707602,
"max": 410.4672131147541,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 48783.0,
"max": 50094.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49636.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49636.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.489582061767578,
"min": 0.17538486421108246,
"max": 2.5607941150665283,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1625.697021484375,
"min": 21.221569061279297,
"max": 1688.553466796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9041970622302196,
"min": 1.74537768836849,
"max": 4.048847931535948,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2549.4406816363335,
"min": 211.19070029258728,
"max": 2676.322982788086,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9041970622302196,
"min": 1.74537768836849,
"max": 4.048847931535948,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2549.4406816363335,
"min": 211.19070029258728,
"max": 2676.322982788086,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017218475508788186,
"min": 0.01332926090884333,
"max": 0.01974751991510857,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05165542652636455,
"min": 0.02665852181768666,
"max": 0.056826377176912496,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057570830649799766,
"min": 0.021775139309465882,
"max": 0.060986262684067094,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1727124919493993,
"min": 0.043550278618931765,
"max": 0.1773493758092324,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.907198697633341e-06,
"min": 3.907198697633341e-06,
"max": 0.00029534167655277503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1721596092900025e-05,
"min": 1.1721596092900025e-05,
"max": 0.0008440957686347498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130236666666666,
"min": 0.10130236666666666,
"max": 0.19844722499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039071,
"min": 0.20773965000000005,
"max": 0.5813652500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.498809666666679e-05,
"min": 7.498809666666679e-05,
"max": 0.0049225165274999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022496429000000036,
"min": 0.00022496429000000036,
"max": 0.014070125974999997,
"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": "1712814829",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712817270"
},
"total": 2441.267510863,
"count": 1,
"self": 0.44331945100020675,
"children": {
"run_training.setup": {
"total": 0.053549682000038956,
"count": 1,
"self": 0.053549682000038956
},
"TrainerController.start_learning": {
"total": 2440.7706417299996,
"count": 1,
"self": 4.380125265985043,
"children": {
"TrainerController._reset_env": {
"total": 2.604498755999998,
"count": 1,
"self": 2.604498755999998
},
"TrainerController.advance": {
"total": 2433.6629503410145,
"count": 233677,
"self": 4.669391711837761,
"children": {
"env_step": {
"total": 1956.1989815700597,
"count": 233677,
"self": 1621.0645364348634,
"children": {
"SubprocessEnvManager._take_step": {
"total": 332.1685034850751,
"count": 233677,
"self": 16.916009385115785,
"children": {
"TorchPolicy.evaluate": {
"total": 315.25249409995934,
"count": 223021,
"self": 315.25249409995934
}
}
},
"workers": {
"total": 2.965941650121181,
"count": 233677,
"self": 0.0,
"children": {
"worker_root": {
"total": 2433.3477412599814,
"count": 233677,
"is_parallel": true,
"self": 1124.3972003349945,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008126159999619631,
"count": 1,
"is_parallel": true,
"self": 0.00020530500012228003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006073109998396831,
"count": 2,
"is_parallel": true,
"self": 0.0006073109998396831
}
}
},
"UnityEnvironment.step": {
"total": 0.030577956000001905,
"count": 1,
"is_parallel": true,
"self": 0.00040394200004811864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021170399998027278,
"count": 1,
"is_parallel": true,
"self": 0.00021170399998027278
},
"communicator.exchange": {
"total": 0.029169319999937215,
"count": 1,
"is_parallel": true,
"self": 0.029169319999937215
},
"steps_from_proto": {
"total": 0.0007929900000362977,
"count": 1,
"is_parallel": true,
"self": 0.00021346500011532044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005795249999209773,
"count": 2,
"is_parallel": true,
"self": 0.0005795249999209773
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1308.9505409249869,
"count": 233676,
"is_parallel": true,
"self": 39.26821843284415,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.64788817701935,
"count": 233676,
"is_parallel": true,
"self": 86.64788817701935
},
"communicator.exchange": {
"total": 1090.1497749090104,
"count": 233676,
"is_parallel": true,
"self": 1090.1497749090104
},
"steps_from_proto": {
"total": 92.88465940611286,
"count": 233676,
"is_parallel": true,
"self": 35.26099395213623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.62366545397663,
"count": 467352,
"is_parallel": true,
"self": 57.62366545397663
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.79457705911693,
"count": 233677,
"self": 6.596280865102926,
"children": {
"process_trajectory": {
"total": 160.41198940101117,
"count": 233677,
"self": 159.0705650910113,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3414243099998657,
"count": 10,
"self": 1.3414243099998657
}
}
},
"_update_policy": {
"total": 305.78630679300284,
"count": 97,
"self": 244.49113979799358,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.295166995009254,
"count": 2910,
"self": 61.295166995009254
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.890000001178123e-07,
"count": 1,
"self": 9.890000001178123e-07
},
"TrainerController._save_models": {
"total": 0.12306637800020326,
"count": 1,
"self": 0.0019864870005221746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12107989099968108,
"count": 1,
"self": 0.12107989099968108
}
}
}
}
}
}
}