ppo-Huggy / run_logs /timers.json
LorChak's picture
Huggy
b71ec89 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3984415531158447,
"min": 1.3984415531158447,
"max": 1.4259240627288818,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69110.984375,
"min": 67846.515625,
"max": 76362.59375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.79838709677419,
"min": 80.40228013029316,
"max": 379.7251908396947,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49500.0,
"min": 48833.0,
"max": 50340.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49844.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49844.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3660356998443604,
"min": 0.12452875822782516,
"max": 2.5029664039611816,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1173.5537109375,
"min": 16.935911178588867,
"max": 1495.58447265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5848820300832873,
"min": 1.7251035338815521,
"max": 4.017812889208228,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1778.1014869213104,
"min": 234.61408060789108,
"max": 2370.5096046328545,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5848820300832873,
"min": 1.7251035338815521,
"max": 4.017812889208228,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1778.1014869213104,
"min": 234.61408060789108,
"max": 2370.5096046328545,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014751868631153936,
"min": 0.013593143876641988,
"max": 0.019761950820167032,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04425560589346181,
"min": 0.027186287753283977,
"max": 0.059285852460501096,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04907242461211151,
"min": 0.020868904267748196,
"max": 0.06530920581685172,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14721727383633454,
"min": 0.04173780853549639,
"max": 0.19592761745055517,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6295487901833237e-06,
"min": 3.6295487901833237e-06,
"max": 0.00029532435155855,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.088864637054997e-05,
"min": 1.088864637054997e-05,
"max": 0.0008438818687060499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120981666666666,
"min": 0.10120981666666666,
"max": 0.19844145000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30362944999999997,
"min": 0.20763065000000003,
"max": 0.5812939500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.036985166666653e-05,
"min": 7.036985166666653e-05,
"max": 0.004922228355000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021110955499999959,
"min": 0.00021110955499999959,
"max": 0.014066568104999996,
"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": "1732313737",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732316447"
},
"total": 2709.655625608,
"count": 1,
"self": 0.425305741000102,
"children": {
"run_training.setup": {
"total": 0.10505819200000133,
"count": 1,
"self": 0.10505819200000133
},
"TrainerController.start_learning": {
"total": 2709.125261675,
"count": 1,
"self": 4.954006136952557,
"children": {
"TrainerController._reset_env": {
"total": 5.443556497999992,
"count": 1,
"self": 5.443556497999992
},
"TrainerController.advance": {
"total": 2698.601654639047,
"count": 232319,
"self": 5.317211668950222,
"children": {
"env_step": {
"total": 2139.1477077080826,
"count": 232319,
"self": 1683.7784107490247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 452.22371894402227,
"count": 232319,
"self": 17.216257507047317,
"children": {
"TorchPolicy.evaluate": {
"total": 435.00746143697495,
"count": 223006,
"self": 435.00746143697495
}
}
},
"workers": {
"total": 3.14557801503571,
"count": 232319,
"self": 0.0,
"children": {
"worker_root": {
"total": 2701.1998587930198,
"count": 232319,
"is_parallel": true,
"self": 1336.2328138119753,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010232660000042415,
"count": 1,
"is_parallel": true,
"self": 0.00029253899998593624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007307270000183053,
"count": 2,
"is_parallel": true,
"self": 0.0007307270000183053
}
}
},
"UnityEnvironment.step": {
"total": 0.060501156000015044,
"count": 1,
"is_parallel": true,
"self": 0.00041297800007100705,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002380519999860553,
"count": 1,
"is_parallel": true,
"self": 0.0002380519999860553
},
"communicator.exchange": {
"total": 0.059073953999984496,
"count": 1,
"is_parallel": true,
"self": 0.059073953999984496
},
"steps_from_proto": {
"total": 0.0007761719999734851,
"count": 1,
"is_parallel": true,
"self": 0.00024131399999305359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005348579999804315,
"count": 2,
"is_parallel": true,
"self": 0.0005348579999804315
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1364.9670449810444,
"count": 232318,
"is_parallel": true,
"self": 40.53519052205934,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.27161827697807,
"count": 232318,
"is_parallel": true,
"self": 93.27161827697807
},
"communicator.exchange": {
"total": 1134.088820624019,
"count": 232318,
"is_parallel": true,
"self": 1134.088820624019
},
"steps_from_proto": {
"total": 97.07141555798819,
"count": 232318,
"is_parallel": true,
"self": 37.2470221450111,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.82439341297709,
"count": 464636,
"is_parallel": true,
"self": 59.82439341297709
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 554.1367352620141,
"count": 232319,
"self": 7.246846902931566,
"children": {
"process_trajectory": {
"total": 189.8406268060814,
"count": 232319,
"self": 188.38664293308085,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4539838730005386,
"count": 10,
"self": 1.4539838730005386
}
}
},
"_update_policy": {
"total": 357.0492615530011,
"count": 97,
"self": 288.59423776900906,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.45502378399203,
"count": 2910,
"self": 68.45502378399203
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0730000212788582e-06,
"count": 1,
"self": 1.0730000212788582e-06
},
"TrainerController._save_models": {
"total": 0.1260433280003781,
"count": 1,
"self": 0.0022793200000705838,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12376400800030751,
"count": 1,
"self": 0.12376400800030751
}
}
}
}
}
}
}