ppo-WormV2 / run_logs /timers.json
AliCampbellKhaya's picture
First Training
205aaf2
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Worm.Policy.Entropy.mean": {
"value": 0.9332621693611145,
"min": 0.9332621693611145,
"max": 1.4094127416610718,
"count": 33
},
"Worm.Policy.Entropy.sum": {
"value": 27997.865234375,
"min": 27997.865234375,
"max": 42282.3828125,
"count": 33
},
"Worm.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 33
},
"Worm.Environment.EpisodeLength.sum": {
"value": 29970.0,
"min": 29970.0,
"max": 29970.0,
"count": 33
},
"Worm.Step.mean": {
"value": 989000.0,
"min": 29000.0,
"max": 989000.0,
"count": 33
},
"Worm.Step.sum": {
"value": 989000.0,
"min": 29000.0,
"max": 989000.0,
"count": 33
},
"Worm.Policy.ExtrinsicValueEstimate.mean": {
"value": 92.3568344116211,
"min": -0.1041359081864357,
"max": 92.3568344116211,
"count": 33
},
"Worm.Policy.ExtrinsicValueEstimate.sum": {
"value": 2770.705078125,
"min": -3.0199413299560547,
"max": 2770.705078125,
"count": 33
},
"Worm.Environment.CumulativeReward.mean": {
"value": 499.41368509928384,
"min": 0.37275360582460615,
"max": 499.41368509928384,
"count": 33
},
"Worm.Environment.CumulativeReward.sum": {
"value": 14982.410552978516,
"min": 10.809854568913579,
"max": 14982.410552978516,
"count": 33
},
"Worm.Policy.ExtrinsicReward.mean": {
"value": 499.41368509928384,
"min": 0.37275360582460615,
"max": 499.41368509928384,
"count": 33
},
"Worm.Policy.ExtrinsicReward.sum": {
"value": 14982.410552978516,
"min": 10.809854568913579,
"max": 14982.410552978516,
"count": 33
},
"Worm.Losses.PolicyLoss.mean": {
"value": 0.06862876058307471,
"min": 0.06610843558188632,
"max": 0.07451005635872035,
"count": 33
},
"Worm.Losses.PolicyLoss.sum": {
"value": 0.20588628174922413,
"min": 0.1490201127174407,
"max": 0.2194609105479794,
"count": 33
},
"Worm.Losses.ValueLoss.mean": {
"value": 8.798186574906026,
"min": 0.0015538716646464558,
"max": 8.798186574906026,
"count": 33
},
"Worm.Losses.ValueLoss.sum": {
"value": 26.39455972471808,
"min": 0.004661614993939367,
"max": 26.39455972471808,
"count": 33
},
"Worm.Policy.LearningRate.mean": {
"value": 9.000097000000007e-06,
"min": 9.000097000000007e-06,
"max": 0.00029550000149999997,
"count": 33
},
"Worm.Policy.LearningRate.sum": {
"value": 2.7000291000000022e-05,
"min": 2.7000291000000022e-05,
"max": 0.0008640000120000001,
"count": 33
},
"Worm.Policy.Epsilon.mean": {
"value": 0.10300000000000002,
"min": 0.10300000000000002,
"max": 0.1985,
"count": 33
},
"Worm.Policy.Epsilon.sum": {
"value": 0.30900000000000005,
"min": 0.30900000000000005,
"max": 0.588,
"count": 33
},
"Worm.Policy.Beta.mean": {
"value": 3.970000000000002e-05,
"min": 3.970000000000002e-05,
"max": 0.0009851500000000002,
"count": 33
},
"Worm.Policy.Beta.sum": {
"value": 0.00011910000000000008,
"min": 0.00011910000000000008,
"max": 0.0028812,
"count": 33
},
"Worm.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Worm.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683736597",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=WormV2 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683739340"
},
"total": 2743.056461904,
"count": 1,
"self": 1.0102541579999524,
"children": {
"run_training.setup": {
"total": 0.05324982699994507,
"count": 1,
"self": 0.05324982699994507
},
"TrainerController.start_learning": {
"total": 2741.992957919,
"count": 1,
"self": 3.4830233229154146,
"children": {
"TrainerController._reset_env": {
"total": 1.1505563129999246,
"count": 1,
"self": 1.1505563129999246
},
"TrainerController.advance": {
"total": 2737.157325843085,
"count": 101000,
"self": 3.4175357641261144,
"children": {
"env_step": {
"total": 1624.230164187003,
"count": 101000,
"self": 1417.2375906089464,
"children": {
"SubprocessEnvManager._take_step": {
"total": 204.78081145904434,
"count": 101000,
"self": 12.839693968966003,
"children": {
"TorchPolicy.evaluate": {
"total": 191.94111749007834,
"count": 101000,
"self": 191.94111749007834
}
}
},
"workers": {
"total": 2.2117621190124055,
"count": 101000,
"self": 0.0,
"children": {
"worker_root": {
"total": 2734.1545727949488,
"count": 101000,
"is_parallel": true,
"self": 1528.1773430689332,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001635250000049382,
"count": 1,
"is_parallel": true,
"self": 0.00039917100002639927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012360790000229827,
"count": 2,
"is_parallel": true,
"self": 0.0012360790000229827
}
}
},
"UnityEnvironment.step": {
"total": 0.04429163600002539,
"count": 1,
"is_parallel": true,
"self": 0.0002626279999731196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036722900006225245,
"count": 1,
"is_parallel": true,
"self": 0.00036722900006225245
},
"communicator.exchange": {
"total": 0.04296338500000729,
"count": 1,
"is_parallel": true,
"self": 0.04296338500000729
},
"steps_from_proto": {
"total": 0.0006983939999827271,
"count": 1,
"is_parallel": true,
"self": 0.00021564599990142597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048274800008130114,
"count": 2,
"is_parallel": true,
"self": 0.00048274800008130114
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1205.9772297260156,
"count": 100999,
"is_parallel": true,
"self": 27.8129571820225,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 34.688485329957985,
"count": 100999,
"is_parallel": true,
"self": 34.688485329957985
},
"communicator.exchange": {
"total": 1076.7973445380107,
"count": 100999,
"is_parallel": true,
"self": 1076.7973445380107
},
"steps_from_proto": {
"total": 66.67844267602436,
"count": 100999,
"is_parallel": true,
"self": 20.653043490092728,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.02539918593163,
"count": 201998,
"is_parallel": true,
"self": 46.02539918593163
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1109.5096258919557,
"count": 101000,
"self": 4.704174843883266,
"children": {
"process_trajectory": {
"total": 88.69639221906948,
"count": 101000,
"self": 88.16224313506939,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5341490840000915,
"count": 2,
"self": 0.5341490840000915
}
}
},
"_update_policy": {
"total": 1016.109058829003,
"count": 100,
"self": 206.09358887700375,
"children": {
"TorchPPOOptimizer.update": {
"total": 810.0154699519992,
"count": 23400,
"self": 810.0154699519992
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4620000001741573e-06,
"count": 1,
"self": 1.4620000001741573e-06
},
"TrainerController._save_models": {
"total": 0.2020509779999884,
"count": 1,
"self": 0.004155509000156599,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1978954689998318,
"count": 1,
"self": 0.1978954689998318
}
}
}
}
}
}
}