ppo-Huggy / run_logs /timers.json
maxxime's picture
Huggy
7201ce9 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4025559425354004,
"min": 1.4025559425354004,
"max": 1.4256845712661743,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71275.0859375,
"min": 68889.3125,
"max": 78097.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.72255192878339,
"min": 70.09463276836158,
"max": 411.4308943089431,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49689.0,
"min": 48918.0,
"max": 50606.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999703.0,
"min": 49980.0,
"max": 1999703.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999703.0,
"min": 49980.0,
"max": 1999703.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4997501373291016,
"min": 0.055482398718595505,
"max": 2.509092330932617,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1684.8316650390625,
"min": 6.768852710723877,
"max": 1751.2840576171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8887302828648678,
"min": 1.8836875086436506,
"max": 4.038821320364795,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2621.004210650921,
"min": 229.80987605452538,
"max": 2728.1859632134438,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8887302828648678,
"min": 1.8836875086436506,
"max": 4.038821320364795,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2621.004210650921,
"min": 229.80987605452538,
"max": 2728.1859632134438,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0178359689268594,
"min": 0.014284627433031952,
"max": 0.021581742768830736,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0535079067805782,
"min": 0.029162770373538177,
"max": 0.056861924430995706,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06249354018105401,
"min": 0.02343791254485647,
"max": 0.06249354018105401,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18748062054316203,
"min": 0.04687582508971294,
"max": 0.18748062054316203,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.510848829750006e-06,
"min": 3.510848829750006e-06,
"max": 0.000295258426580525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0532546489250019e-05,
"min": 1.0532546489250019e-05,
"max": 0.0008438953687015498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117025000000002,
"min": 0.10117025000000002,
"max": 0.198419475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30351075000000005,
"min": 0.20746774999999998,
"max": 0.58129845,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.839547500000013e-05,
"min": 6.839547500000013e-05,
"max": 0.004921131802500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002051864250000004,
"min": 0.0002051864250000004,
"max": 0.014066792655,
"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": "1785328975",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1785331641"
},
"total": 2665.916633365,
"count": 1,
"self": 0.4933710299997074,
"children": {
"run_training.setup": {
"total": 0.024903248000100575,
"count": 1,
"self": 0.024903248000100575
},
"TrainerController.start_learning": {
"total": 2665.3983590870002,
"count": 1,
"self": 4.409853399834901,
"children": {
"TrainerController._reset_env": {
"total": 3.613674781999862,
"count": 1,
"self": 3.613674781999862
},
"TrainerController.advance": {
"total": 2657.2674940041657,
"count": 233446,
"self": 4.507280367210569,
"children": {
"env_step": {
"total": 2171.68142338804,
"count": 233446,
"self": 1739.9218229251057,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.01582793489365,
"count": 233446,
"self": 16.01228618379173,
"children": {
"TorchPolicy.evaluate": {
"total": 413.0035417511019,
"count": 223002,
"self": 413.0035417511019
}
}
},
"workers": {
"total": 2.7437725280406084,
"count": 233446,
"self": 0.0,
"children": {
"worker_root": {
"total": 2652.6210842669743,
"count": 233446,
"is_parallel": true,
"self": 1249.0768633550103,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008046540001487301,
"count": 1,
"is_parallel": true,
"self": 0.00022453900010077632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005801150000479538,
"count": 2,
"is_parallel": true,
"self": 0.0005801150000479538
}
}
},
"UnityEnvironment.step": {
"total": 0.06077628000002733,
"count": 1,
"is_parallel": true,
"self": 0.0002785639999274281,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000221680000095148,
"count": 1,
"is_parallel": true,
"self": 0.000221680000095148
},
"communicator.exchange": {
"total": 0.05965440699992541,
"count": 1,
"is_parallel": true,
"self": 0.05965440699992541
},
"steps_from_proto": {
"total": 0.0006216290000793379,
"count": 1,
"is_parallel": true,
"self": 0.00016642400009914127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004552049999801966,
"count": 2,
"is_parallel": true,
"self": 0.0004552049999801966
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1403.544220911964,
"count": 233445,
"is_parallel": true,
"self": 38.2420198849245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.26195031197426,
"count": 233445,
"is_parallel": true,
"self": 84.26195031197426
},
"communicator.exchange": {
"total": 1189.8613720979624,
"count": 233445,
"is_parallel": true,
"self": 1189.8613720979624
},
"steps_from_proto": {
"total": 91.17887861710278,
"count": 233445,
"is_parallel": true,
"self": 32.97409111504089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.20478750206189,
"count": 466890,
"is_parallel": true,
"self": 58.20478750206189
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.07879024891486,
"count": 233446,
"self": 6.686015752890626,
"children": {
"process_trajectory": {
"total": 164.96247113902314,
"count": 233446,
"self": 163.87668697002414,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0857841689989982,
"count": 10,
"self": 1.0857841689989982
}
}
},
"_update_policy": {
"total": 309.4303033570011,
"count": 97,
"self": 246.34661212301762,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.08369123398347,
"count": 2910,
"self": 63.08369123398347
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.109999155043624e-07,
"count": 1,
"self": 9.109999155043624e-07
},
"TrainerController._save_models": {
"total": 0.10733599000013783,
"count": 1,
"self": 0.0013120159992467961,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10602397400089103,
"count": 1,
"self": 0.10602397400089103
}
}
}
}
}
}
}