ppo-Huggy / run_logs /timers.json
PideyZ's picture
Huggy
b71cfe8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100239276885986,
"min": 1.4100239276885986,
"max": 1.4316964149475098,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70585.796875,
"min": 69316.6953125,
"max": 76057.4453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.88045540796963,
"min": 88.88669064748201,
"max": 405.2096774193548,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49475.0,
"min": 49122.0,
"max": 50246.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999936.0,
"min": 49869.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999936.0,
"min": 49869.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.37725567817688,
"min": 0.14869344234466553,
"max": 2.4276630878448486,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1252.813720703125,
"min": 18.28929328918457,
"max": 1308.748291015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7387899127585613,
"min": 1.794282229814103,
"max": 3.8727604966414604,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1970.3422840237617,
"min": 220.69671426713467,
"max": 2079.562495291233,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7387899127585613,
"min": 1.794282229814103,
"max": 3.8727604966414604,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1970.3422840237617,
"min": 220.69671426713467,
"max": 2079.562495291233,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016556412597452032,
"min": 0.013529081060551108,
"max": 0.021550460736519502,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049669237792356095,
"min": 0.027058162121102215,
"max": 0.0553396077050517,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04958824734720919,
"min": 0.022090477931002776,
"max": 0.06012916875382264,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14876474204162757,
"min": 0.04418095586200555,
"max": 0.17513974967102208,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.312098896000003e-06,
"min": 3.312098896000003e-06,
"max": 0.000295232926589025,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.936296688000008e-06,
"min": 9.936296688000008e-06,
"max": 0.0008437548187484,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110399999999997,
"min": 0.10110399999999997,
"max": 0.198410975,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033119999999999,
"min": 0.20733795,
"max": 0.5812516,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.508960000000007e-05,
"min": 6.508960000000007e-05,
"max": 0.004920707652500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001952688000000002,
"min": 0.0001952688000000002,
"max": 0.01406445484,
"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": "1731863887",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1731866498"
},
"total": 2611.153941451,
"count": 1,
"self": 0.43832082600010835,
"children": {
"run_training.setup": {
"total": 0.05827473799990912,
"count": 1,
"self": 0.05827473799990912
},
"TrainerController.start_learning": {
"total": 2610.657345887,
"count": 1,
"self": 4.742249201040067,
"children": {
"TrainerController._reset_env": {
"total": 5.962714278000021,
"count": 1,
"self": 5.962714278000021
},
"TrainerController.advance": {
"total": 2599.8358708849596,
"count": 231536,
"self": 4.807689176023359,
"children": {
"env_step": {
"total": 2047.4156275130204,
"count": 231536,
"self": 1610.7300392111483,
"children": {
"SubprocessEnvManager._take_step": {
"total": 433.6919959649658,
"count": 231536,
"self": 16.443196828007103,
"children": {
"TorchPolicy.evaluate": {
"total": 417.2487991369587,
"count": 222970,
"self": 417.2487991369587
}
}
},
"workers": {
"total": 2.993592336906204,
"count": 231536,
"self": 0.0,
"children": {
"worker_root": {
"total": 2602.815678593007,
"count": 231536,
"is_parallel": true,
"self": 1294.4710860340838,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008549330000278133,
"count": 1,
"is_parallel": true,
"self": 0.00024629800032016647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006086349997076468,
"count": 2,
"is_parallel": true,
"self": 0.0006086349997076468
}
}
},
"UnityEnvironment.step": {
"total": 0.03212498799985042,
"count": 1,
"is_parallel": true,
"self": 0.00036649699973168026,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022435500000028696,
"count": 1,
"is_parallel": true,
"self": 0.00022435500000028696
},
"communicator.exchange": {
"total": 0.030739578000066103,
"count": 1,
"is_parallel": true,
"self": 0.030739578000066103
},
"steps_from_proto": {
"total": 0.0007945580000523478,
"count": 1,
"is_parallel": true,
"self": 0.00019569800019780814,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005988599998545396,
"count": 2,
"is_parallel": true,
"self": 0.0005988599998545396
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1308.344592558923,
"count": 231535,
"is_parallel": true,
"self": 39.081863468820984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.0876669920417,
"count": 231535,
"is_parallel": true,
"self": 87.0876669920417
},
"communicator.exchange": {
"total": 1088.476000328079,
"count": 231535,
"is_parallel": true,
"self": 1088.476000328079
},
"steps_from_proto": {
"total": 93.69906176998143,
"count": 231535,
"is_parallel": true,
"self": 35.62569313201061,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.073368637970816,
"count": 463070,
"is_parallel": true,
"self": 58.073368637970816
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 547.6125541959161,
"count": 231536,
"self": 7.214624313985041,
"children": {
"process_trajectory": {
"total": 173.39574366192824,
"count": 231536,
"self": 172.11952912792822,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2762145340000188,
"count": 10,
"self": 1.2762145340000188
}
}
},
"_update_policy": {
"total": 367.00218622000284,
"count": 97,
"self": 297.2077986790173,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.79438754098555,
"count": 2910,
"self": 69.79438754098555
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0710000424296595e-06,
"count": 1,
"self": 1.0710000424296595e-06
},
"TrainerController._save_models": {
"total": 0.11651045200005683,
"count": 1,
"self": 0.0022972659999140888,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11421318600014274,
"count": 1,
"self": 0.11421318600014274
}
}
}
}
}
}
}