ppo-Huggy / run_logs /timers.json
Huav's picture
Huggy
0cc0baf verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4031364917755127,
"min": 1.4031364917755127,
"max": 1.4287822246551514,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70711.0625,
"min": 66819.0625,
"max": 78926.25,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.17904761904762,
"min": 85.49653979238754,
"max": 448.36607142857144,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49444.0,
"min": 48966.0,
"max": 50217.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999905.0,
"min": 49719.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999905.0,
"min": 49719.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4359002113342285,
"min": 0.11847992986440659,
"max": 2.5527777671813965,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1278.84765625,
"min": 13.15127182006836,
"max": 1402.037841796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.746228062765939,
"min": 1.6581611033226993,
"max": 4.130690130535162,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1966.769732952118,
"min": 184.05588246881962,
"max": 2257.764464855194,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.746228062765939,
"min": 1.6581611033226993,
"max": 4.130690130535162,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1966.769732952118,
"min": 184.05588246881962,
"max": 2257.764464855194,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016391499007780416,
"min": 0.013776421800462735,
"max": 0.02028819706562596,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03278299801556083,
"min": 0.0285720072381082,
"max": 0.056643336845445445,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05387248732149601,
"min": 0.02001747153699398,
"max": 0.06276734502365192,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10774497464299201,
"min": 0.04003494307398796,
"max": 0.1782396929959456,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.5273234909250135e-06,
"min": 4.5273234909250135e-06,
"max": 0.00029530102656632497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.054646981850027e-06,
"min": 9.054646981850027e-06,
"max": 0.0008439919686693501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101509075,
"min": 0.101509075,
"max": 0.198433675,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20301815,
"min": 0.20301815,
"max": 0.5813306500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.53028425000002e-05,
"min": 8.53028425000002e-05,
"max": 0.004921840382499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001706056850000004,
"min": 0.0001706056850000004,
"max": 0.014068399435000004,
"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": "1769232597",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769235486"
},
"total": 2888.9920316099997,
"count": 1,
"self": 0.549349109999639,
"children": {
"run_training.setup": {
"total": 0.028171098000029815,
"count": 1,
"self": 0.028171098000029815
},
"TrainerController.start_learning": {
"total": 2888.414511402,
"count": 1,
"self": 5.025751873943136,
"children": {
"TrainerController._reset_env": {
"total": 3.714435461999983,
"count": 1,
"self": 3.714435461999983
},
"TrainerController.advance": {
"total": 2879.5641983600576,
"count": 231908,
"self": 5.059312207081803,
"children": {
"env_step": {
"total": 2372.115580426945,
"count": 231908,
"self": 1905.43410364596,
"children": {
"SubprocessEnvManager._take_step": {
"total": 463.49930343001915,
"count": 231908,
"self": 17.671672780071503,
"children": {
"TorchPolicy.evaluate": {
"total": 445.82763064994765,
"count": 222990,
"self": 445.82763064994765
}
}
},
"workers": {
"total": 3.182173350965968,
"count": 231908,
"self": 0.0,
"children": {
"worker_root": {
"total": 2874.113520166995,
"count": 231908,
"is_parallel": true,
"self": 1336.5153614210278,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009809289999793691,
"count": 1,
"is_parallel": true,
"self": 0.00029651299996658054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006844160000127886,
"count": 2,
"is_parallel": true,
"self": 0.0006844160000127886
}
}
},
"UnityEnvironment.step": {
"total": 0.033756698999923174,
"count": 1,
"is_parallel": true,
"self": 0.00028284299992265005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022613300006923964,
"count": 1,
"is_parallel": true,
"self": 0.00022613300006923964
},
"communicator.exchange": {
"total": 0.03254530300000624,
"count": 1,
"is_parallel": true,
"self": 0.03254530300000624
},
"steps_from_proto": {
"total": 0.0007024199999250413,
"count": 1,
"is_parallel": true,
"self": 0.0001934859997163585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005089340002086828,
"count": 2,
"is_parallel": true,
"self": 0.0005089340002086828
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1537.598158745967,
"count": 231907,
"is_parallel": true,
"self": 42.45808920900731,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 95.30973302585471,
"count": 231907,
"is_parallel": true,
"self": 95.30973302585471
},
"communicator.exchange": {
"total": 1298.8978405671219,
"count": 231907,
"is_parallel": true,
"self": 1298.8978405671219
},
"steps_from_proto": {
"total": 100.93249594398321,
"count": 231907,
"is_parallel": true,
"self": 36.23644695800522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.696048985978,
"count": 463814,
"is_parallel": true,
"self": 64.696048985978
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 502.38930572603067,
"count": 231908,
"self": 7.236301867034626,
"children": {
"process_trajectory": {
"total": 171.5061608349954,
"count": 231908,
"self": 170.21386349999557,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2922973349998301,
"count": 10,
"self": 1.2922973349998301
}
}
},
"_update_policy": {
"total": 323.64684302400065,
"count": 96,
"self": 257.16301001300667,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.48383301099398,
"count": 2880,
"self": 66.48383301099398
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.259993021260016e-07,
"count": 1,
"self": 9.259993021260016e-07
},
"TrainerController._save_models": {
"total": 0.1101247799997509,
"count": 1,
"self": 0.0012980189994777902,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10882676100027311,
"count": 1,
"self": 0.10882676100027311
}
}
}
}
}
}
}