ppo-huggy / run_logs /timers.json
Haining Wang
my first huggy
56408e5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4067695140838623,
"min": 1.4067695140838623,
"max": 1.4270542860031128,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70588.8828125,
"min": 69146.9921875,
"max": 77835.9296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 65.99865951742628,
"min": 65.94765100671141,
"max": 421.7563025210084,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49235.0,
"min": 49131.0,
"max": 50210.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49778.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49778.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5165903568267822,
"min": 0.07350541651248932,
"max": 2.5467844009399414,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1877.37646484375,
"min": 8.673639297485352,
"max": 1877.37646484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.902664911331504,
"min": 1.7700127502114087,
"max": 4.1297355464262555,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2911.388023853302,
"min": 208.8615045249462,
"max": 2929.3617040514946,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.902664911331504,
"min": 1.7700127502114087,
"max": 4.1297355464262555,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2911.388023853302,
"min": 208.8615045249462,
"max": 2929.3617040514946,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01664581179065863,
"min": 0.014241020956008772,
"max": 0.019887812726180225,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04993743537197588,
"min": 0.028482041912017544,
"max": 0.05613566871761577,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05871173391739528,
"min": 0.022484806490441163,
"max": 0.06297929249703883,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17613520175218583,
"min": 0.044969612980882326,
"max": 0.1889378774911165,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.090398636566668e-06,
"min": 4.090398636566668e-06,
"max": 0.00029535570154809996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2271195909700004e-05,
"min": 1.2271195909700004e-05,
"max": 0.00084411286862905,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10136343333333335,
"min": 0.10136343333333335,
"max": 0.19845189999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30409030000000004,
"min": 0.20785860000000006,
"max": 0.58137095,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.803532333333338e-05,
"min": 7.803532333333338e-05,
"max": 0.00492274981,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023410597000000016,
"min": 0.00023410597000000016,
"max": 0.014070410405,
"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": "1670380850",
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670383047"
},
"total": 2197.2932315669996,
"count": 1,
"self": 0.3938193529993441,
"children": {
"run_training.setup": {
"total": 0.1072370059999912,
"count": 1,
"self": 0.1072370059999912
},
"TrainerController.start_learning": {
"total": 2196.792175208,
"count": 1,
"self": 3.9385118549912477,
"children": {
"TrainerController._reset_env": {
"total": 13.189138508999974,
"count": 1,
"self": 13.189138508999974
},
"TrainerController.advance": {
"total": 2179.549699054009,
"count": 233944,
"self": 4.129806180942978,
"children": {
"env_step": {
"total": 1709.837185849043,
"count": 233944,
"self": 1429.0716083840557,
"children": {
"SubprocessEnvManager._take_step": {
"total": 278.2541913500012,
"count": 233944,
"self": 14.74755177397742,
"children": {
"TorchPolicy.evaluate": {
"total": 263.50663957602376,
"count": 222908,
"self": 66.67598949003309,
"children": {
"TorchPolicy.sample_actions": {
"total": 196.83065008599067,
"count": 222908,
"self": 196.83065008599067
}
}
}
}
},
"workers": {
"total": 2.5113861149861805,
"count": 233944,
"self": 0.0,
"children": {
"worker_root": {
"total": 2188.76200876306,
"count": 233944,
"is_parallel": true,
"self": 1011.8139660461638,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021470759999715483,
"count": 1,
"is_parallel": true,
"self": 0.00030696599998236707,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018401099999891812,
"count": 2,
"is_parallel": true,
"self": 0.0018401099999891812
}
}
},
"UnityEnvironment.step": {
"total": 0.02705550799998946,
"count": 1,
"is_parallel": true,
"self": 0.00030573199995842515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019959899998411856,
"count": 1,
"is_parallel": true,
"self": 0.00019959899998411856
},
"communicator.exchange": {
"total": 0.02586126400001376,
"count": 1,
"is_parallel": true,
"self": 0.02586126400001376
},
"steps_from_proto": {
"total": 0.0006889130000331534,
"count": 1,
"is_parallel": true,
"self": 0.00022811000002320725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004608030000099461,
"count": 2,
"is_parallel": true,
"self": 0.0004608030000099461
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1176.948042716896,
"count": 233943,
"is_parallel": true,
"self": 34.230890733967954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.19057674000555,
"count": 233943,
"is_parallel": true,
"self": 74.19057674000555
},
"communicator.exchange": {
"total": 977.1668868899799,
"count": 233943,
"is_parallel": true,
"self": 977.1668868899799
},
"steps_from_proto": {
"total": 91.35968835294273,
"count": 233943,
"is_parallel": true,
"self": 37.765872980003394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.59381537293933,
"count": 467886,
"is_parallel": true,
"self": 53.59381537293933
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 465.5827070240232,
"count": 233944,
"self": 5.748707084974228,
"children": {
"process_trajectory": {
"total": 155.54273142804925,
"count": 233944,
"self": 155.0620235310497,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4807078969995473,
"count": 4,
"self": 0.4807078969995473
}
}
},
"_update_policy": {
"total": 304.2912685109997,
"count": 97,
"self": 250.74623272299874,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.54503578800097,
"count": 2910,
"self": 53.54503578800097
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.779999577905983e-07,
"count": 1,
"self": 7.779999577905983e-07
},
"TrainerController._save_models": {
"total": 0.11482501199998296,
"count": 1,
"self": 0.0020678809996752534,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11275713100030771,
"count": 1,
"self": 0.11275713100030771
}
}
}
}
}
}
}