ppo-Huggy / run_logs /timers.json
wuwx's picture
Huggy
48c38a0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4018771648406982,
"min": 1.4018771648406982,
"max": 1.4274941682815552,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68652.7265625,
"min": 68652.7265625,
"max": 77038.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.91708126036484,
"min": 75.01519756838906,
"max": 417.625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49396.0,
"min": 49000.0,
"max": 50115.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999913.0,
"min": 49689.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999913.0,
"min": 49689.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.492236375808716,
"min": 0.0413089245557785,
"max": 2.530951738357544,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1502.8184814453125,
"min": 4.915761947631836,
"max": 1623.85986328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.719862240562787,
"min": 1.8697948771364548,
"max": 3.97157312625773,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2243.0769310593605,
"min": 222.50559037923813,
"max": 2548.126562535763,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.719862240562787,
"min": 1.8697948771364548,
"max": 3.97157312625773,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2243.0769310593605,
"min": 222.50559037923813,
"max": 2548.126562535763,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015009708170610895,
"min": 0.012449522492412749,
"max": 0.01998803026896591,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045029124511832684,
"min": 0.024899044984825498,
"max": 0.0557426494245495,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06062526375883156,
"min": 0.023871142355104284,
"max": 0.06189776162306468,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18187579127649467,
"min": 0.04774228471020857,
"max": 0.18241037006179492,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5315988228333313e-06,
"min": 3.5315988228333313e-06,
"max": 0.0002953670265443249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0594796468499994e-05,
"min": 1.0594796468499994e-05,
"max": 0.0008441856186047999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117716666666669,
"min": 0.10117716666666669,
"max": 0.198455675,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353150000000007,
"min": 0.20756280000000005,
"max": 0.5813951999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.874061666666666e-05,
"min": 6.874061666666666e-05,
"max": 0.0049229381824999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020622184999999997,
"min": 0.00020622184999999997,
"max": 0.01407162048,
"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": "1702823401",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702825817"
},
"total": 2415.701117074,
"count": 1,
"self": 0.4445271920003506,
"children": {
"run_training.setup": {
"total": 0.05096216299995149,
"count": 1,
"self": 0.05096216299995149
},
"TrainerController.start_learning": {
"total": 2415.205627719,
"count": 1,
"self": 4.480555786026343,
"children": {
"TrainerController._reset_env": {
"total": 3.443621726999993,
"count": 1,
"self": 3.443621726999993
},
"TrainerController.advance": {
"total": 2407.1630811049736,
"count": 233288,
"self": 4.929156118874289,
"children": {
"env_step": {
"total": 1901.452070874061,
"count": 233288,
"self": 1579.9164367520807,
"children": {
"SubprocessEnvManager._take_step": {
"total": 318.76773010997334,
"count": 233288,
"self": 16.320376417090984,
"children": {
"TorchPolicy.evaluate": {
"total": 302.44735369288236,
"count": 222910,
"self": 302.44735369288236
}
}
},
"workers": {
"total": 2.767904012006966,
"count": 233288,
"self": 0.0,
"children": {
"worker_root": {
"total": 2408.045865299939,
"count": 233288,
"is_parallel": true,
"self": 1124.957583274943,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006808739999542013,
"count": 1,
"is_parallel": true,
"self": 0.00020812099990052957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004727530000536717,
"count": 2,
"is_parallel": true,
"self": 0.0004727530000536717
}
}
},
"UnityEnvironment.step": {
"total": 0.04160083400000758,
"count": 1,
"is_parallel": true,
"self": 0.00033934600003249216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019479700000601952,
"count": 1,
"is_parallel": true,
"self": 0.00019479700000601952
},
"communicator.exchange": {
"total": 0.04037636700002167,
"count": 1,
"is_parallel": true,
"self": 0.04037636700002167
},
"steps_from_proto": {
"total": 0.0006903239999473954,
"count": 1,
"is_parallel": true,
"self": 0.00019246999988808966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004978540000593057,
"count": 2,
"is_parallel": true,
"self": 0.0004978540000593057
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1283.088282024996,
"count": 233287,
"is_parallel": true,
"self": 41.38519630896894,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.32048208104254,
"count": 233287,
"is_parallel": true,
"self": 81.32048208104254
},
"communicator.exchange": {
"total": 1069.7953751180185,
"count": 233287,
"is_parallel": true,
"self": 1069.7953751180185
},
"steps_from_proto": {
"total": 90.58722851696626,
"count": 233287,
"is_parallel": true,
"self": 31.738650341843822,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.84857817512244,
"count": 466574,
"is_parallel": true,
"self": 58.84857817512244
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.7818541120384,
"count": 233288,
"self": 6.660563273001685,
"children": {
"process_trajectory": {
"total": 159.88761850203826,
"count": 233288,
"self": 158.76442786403817,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1231906380000964,
"count": 10,
"self": 1.1231906380000964
}
}
},
"_update_policy": {
"total": 334.23367233699844,
"count": 97,
"self": 269.66977470798963,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.5638976290088,
"count": 2910,
"self": 64.5638976290088
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.018000148178544e-06,
"count": 1,
"self": 1.018000148178544e-06
},
"TrainerController._save_models": {
"total": 0.11836808299995027,
"count": 1,
"self": 0.0020604369997272443,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11630764600022303,
"count": 1,
"self": 0.11630764600022303
}
}
}
}
}
}
}