ppo-Huggy / run_logs /timers.json
quantyi's picture
Huggy
53da79d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4031859636306763,
"min": 1.4031859636306763,
"max": 1.4256937503814697,
"count": 37
},
"Huggy.Policy.Entropy.sum": {
"value": 69488.578125,
"min": 55364.3203125,
"max": 71659.734375,
"count": 37
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.49415692821368,
"min": 72.5979381443299,
"max": 233.0328947368421,
"count": 37
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49414.0,
"min": 35421.0,
"max": 49811.0,
"count": 37
},
"Huggy.Step.mean": {
"value": 1999953.0,
"min": 199884.0,
"max": 1999953.0,
"count": 37
},
"Huggy.Step.sum": {
"value": 1999953.0,
"min": 199884.0,
"max": 1999953.0,
"count": 37
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4812569618225098,
"min": 0.8228601217269897,
"max": 2.5020360946655273,
"count": 37
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1486.27294921875,
"min": 124.25187683105469,
"max": 1662.39208984375,
"count": 37
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.872997135073195,
"min": 3.1528087139919103,
"max": 3.9666562765263595,
"count": 37
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2319.925283908844,
"min": 476.0741158127785,
"max": 2623.2714703679085,
"count": 37
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.872997135073195,
"min": 3.1528087139919103,
"max": 3.9666562765263595,
"count": 37
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2319.925283908844,
"min": 476.0741158127785,
"max": 2623.2714703679085,
"count": 37
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016179299919814285,
"min": 0.014453031715755868,
"max": 0.020166788240506626,
"count": 37
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04853789975944285,
"min": 0.0178361774305813,
"max": 0.06042453281722071,
"count": 37
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057403613709741175,
"min": 0.024376424898703893,
"max": 0.05762834809720516,
"count": 37
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17221084112922352,
"min": 0.024376424898703893,
"max": 0.1728850442916155,
"count": 37
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.071148642983343e-06,
"min": 4.071148642983343e-06,
"max": 0.00027224145925284994,
"count": 37
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.221344592895003e-05,
"min": 1.221344592895003e-05,
"max": 0.00079807188397605,
"count": 37
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10135701666666669,
"min": 0.10135701666666669,
"max": 0.19074715,
"count": 37
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30407105000000006,
"min": 0.19074715,
"max": 0.5660239499999998,
"count": 37
},
"Huggy.Policy.Beta.mean": {
"value": 7.771513166666682e-05,
"min": 7.771513166666682e-05,
"max": 0.004538282785000001,
"count": 37
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023314539500000046,
"min": 0.00023314539500000046,
"max": 0.013304595105000002,
"count": 37
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 37
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 37
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1725556992",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy2 --resume --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1725561285"
},
"total": 4293.654688324001,
"count": 1,
"self": 0.6071345410009599,
"children": {
"run_training.setup": {
"total": 0.07293482499994752,
"count": 1,
"self": 0.07293482499994752
},
"TrainerController.start_learning": {
"total": 4292.974618958,
"count": 1,
"self": 8.336601456009703,
"children": {
"TrainerController._reset_env": {
"total": 2.399193668999942,
"count": 1,
"self": 2.399193668999942
},
"TrainerController.advance": {
"total": 4282.13439088899,
"count": 214243,
"self": 7.979243650024728,
"children": {
"env_step": {
"total": 2770.538145374833,
"count": 214243,
"self": 2325.3783509616514,
"children": {
"SubprocessEnvManager._take_step": {
"total": 439.82710657914527,
"count": 214243,
"self": 28.408440683108665,
"children": {
"TorchPolicy.evaluate": {
"total": 411.4186658960366,
"count": 204608,
"self": 411.4186658960366
}
}
},
"workers": {
"total": 5.332687834036733,
"count": 214243,
"self": 0.0,
"children": {
"worker_root": {
"total": 4279.429088474889,
"count": 214243,
"is_parallel": true,
"self": 2445.5147257178683,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0015267489998223027,
"count": 1,
"is_parallel": true,
"self": 0.00039454699981433805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011322020000079647,
"count": 2,
"is_parallel": true,
"self": 0.0011322020000079647
}
}
},
"UnityEnvironment.step": {
"total": 0.04991000100017118,
"count": 1,
"is_parallel": true,
"self": 0.0005136400000083086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002290360000642977,
"count": 1,
"is_parallel": true,
"self": 0.0002290360000642977
},
"communicator.exchange": {
"total": 0.04821204800009582,
"count": 1,
"is_parallel": true,
"self": 0.04821204800009582
},
"steps_from_proto": {
"total": 0.0009552770000027522,
"count": 1,
"is_parallel": true,
"self": 0.000291549999928975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006637270000737772,
"count": 2,
"is_parallel": true,
"self": 0.0006637270000737772
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1833.9143627570206,
"count": 214242,
"is_parallel": true,
"self": 58.88895836843494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 102.63811282692677,
"count": 214242,
"is_parallel": true,
"self": 102.63811282692677
},
"communicator.exchange": {
"total": 1545.1145868078365,
"count": 214242,
"is_parallel": true,
"self": 1545.1145868078365
},
"steps_from_proto": {
"total": 127.27270475382238,
"count": 214242,
"is_parallel": true,
"self": 41.36639711654084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.90630763728154,
"count": 428484,
"is_parallel": true,
"self": 85.90630763728154
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1503.6170018641321,
"count": 214243,
"self": 11.961143367044315,
"children": {
"process_trajectory": {
"total": 240.89942518108137,
"count": 214243,
"self": 239.5917037860811,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3077213950002715,
"count": 10,
"self": 1.3077213950002715
}
}
},
"_update_policy": {
"total": 1250.7564333160065,
"count": 89,
"self": 319.1099207269924,
"children": {
"TorchPPOOptimizer.update": {
"total": 931.646512589014,
"count": 2670,
"self": 931.646512589014
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.51999936660286e-07,
"count": 1,
"self": 9.51999936660286e-07
},
"TrainerController._save_models": {
"total": 0.10443199200017261,
"count": 1,
"self": 0.005597168999884161,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09883482300028845,
"count": 1,
"self": 0.09883482300028845
}
}
}
}
}
}
}