ppo-Huggy / run_logs /timers.json
esperesa's picture
Huggy
df84b9f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.409393072128296,
"min": 1.409393072128296,
"max": 1.428564190864563,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69445.0234375,
"min": 67912.5625,
"max": 77785.1953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 115.3232558139535,
"min": 98.7011952191235,
"max": 413.6803278688525,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49589.0,
"min": 48807.0,
"max": 50469.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999938.0,
"min": 49842.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999938.0,
"min": 49842.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.264357566833496,
"min": 0.012318098917603493,
"max": 2.3921570777893066,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 973.6737670898438,
"min": 1.4904899597167969,
"max": 1151.43408203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4546213054379753,
"min": 1.9777817967509435,
"max": 3.818185647428036,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1485.4871613383293,
"min": 239.31159740686417,
"max": 1841.0489993691444,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4546213054379753,
"min": 1.9777817967509435,
"max": 3.818185647428036,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1485.4871613383293,
"min": 239.31159740686417,
"max": 1841.0489993691444,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01561886483929508,
"min": 0.013431198293498406,
"max": 0.02015076122977714,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046856594517885236,
"min": 0.02921160458863596,
"max": 0.06045228368933143,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04531782066656483,
"min": 0.024777452802906434,
"max": 0.05761375162336562,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1359534619996945,
"min": 0.04955490560581287,
"max": 0.17284125487009686,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.118498960533333e-06,
"min": 3.118498960533333e-06,
"max": 0.0002952732765755749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.355496881599999e-06,
"min": 9.355496881599999e-06,
"max": 0.0008437057687647497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10103946666666667,
"min": 0.10103946666666667,
"max": 0.19842442500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031184,
"min": 0.20721430000000002,
"max": 0.58123525,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.186938666666666e-05,
"min": 6.186938666666666e-05,
"max": 0.004921378807500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018560816,
"min": 0.00018560816,
"max": 0.014063638975,
"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": "1725026975",
"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 --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": "1725031647"
},
"total": 4672.645964631,
"count": 1,
"self": 0.6998385820006661,
"children": {
"run_training.setup": {
"total": 0.10321637600009126,
"count": 1,
"self": 0.10321637600009126
},
"TrainerController.start_learning": {
"total": 4671.842909673,
"count": 1,
"self": 8.283212731072126,
"children": {
"TrainerController._reset_env": {
"total": 3.6076348490000782,
"count": 1,
"self": 3.6076348490000782
},
"TrainerController.advance": {
"total": 4659.8437477089265,
"count": 231033,
"self": 7.91091000616052,
"children": {
"env_step": {
"total": 2958.575222341744,
"count": 231033,
"self": 2453.028926332679,
"children": {
"SubprocessEnvManager._take_step": {
"total": 499.9456317099364,
"count": 231033,
"self": 31.730183639109327,
"children": {
"TorchPolicy.evaluate": {
"total": 468.21544807082705,
"count": 222892,
"self": 468.21544807082705
}
}
},
"workers": {
"total": 5.600664299128425,
"count": 231033,
"self": 0.0,
"children": {
"worker_root": {
"total": 4658.45943386304,
"count": 231033,
"is_parallel": true,
"self": 2711.254897851068,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001175113000044803,
"count": 1,
"is_parallel": true,
"self": 0.00036458100009895134,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008105319999458516,
"count": 2,
"is_parallel": true,
"self": 0.0008105319999458516
}
}
},
"UnityEnvironment.step": {
"total": 0.03842006399997899,
"count": 1,
"is_parallel": true,
"self": 0.0005761830000210466,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002615559999412653,
"count": 1,
"is_parallel": true,
"self": 0.0002615559999412653
},
"communicator.exchange": {
"total": 0.036613246999991134,
"count": 1,
"is_parallel": true,
"self": 0.036613246999991134
},
"steps_from_proto": {
"total": 0.0009690780000255472,
"count": 1,
"is_parallel": true,
"self": 0.0002449049999313502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000724173000094197,
"count": 2,
"is_parallel": true,
"self": 0.000724173000094197
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1947.2045360119723,
"count": 231032,
"is_parallel": true,
"self": 61.51615909898737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 109.6615286670243,
"count": 231032,
"is_parallel": true,
"self": 109.6615286670243
},
"communicator.exchange": {
"total": 1640.4400688109642,
"count": 231032,
"is_parallel": true,
"self": 1640.4400688109642
},
"steps_from_proto": {
"total": 135.58677943499652,
"count": 231032,
"is_parallel": true,
"self": 43.04977981218565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 92.53699962281087,
"count": 462064,
"is_parallel": true,
"self": 92.53699962281087
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1693.3576153610218,
"count": 231033,
"self": 12.46244322396592,
"children": {
"process_trajectory": {
"total": 243.07928021105454,
"count": 231033,
"self": 241.78698509805372,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2922951130008187,
"count": 10,
"self": 1.2922951130008187
}
}
},
"_update_policy": {
"total": 1437.8158919260013,
"count": 97,
"self": 344.37460847899524,
"children": {
"TorchPPOOptimizer.update": {
"total": 1093.441283447006,
"count": 2910,
"self": 1093.441283447006
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0040002962341532e-06,
"count": 1,
"self": 1.0040002962341532e-06
},
"TrainerController._save_models": {
"total": 0.10831338000025426,
"count": 1,
"self": 0.0029183980004745536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1053949819997797,
"count": 1,
"self": 0.1053949819997797
}
}
}
}
}
}
}