ppo-Huggy / run_logs /timers.json
saifyxpro's picture
Huggy trained agent
7483573 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408027172088623,
"min": 1.408027172088623,
"max": 1.4271403551101685,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70728.0234375,
"min": 69406.1875,
"max": 76640.515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.12121212121212,
"min": 74.1987951807229,
"max": 402.2741935483871,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49436.0,
"min": 48785.0,
"max": 50096.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49786.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49786.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.487933397293091,
"min": 0.13894827663898468,
"max": 2.4930577278137207,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1395.7305908203125,
"min": 17.09063720703125,
"max": 1614.50732421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.776118955191444,
"min": 1.8665355785590847,
"max": 3.953741100735552,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2118.4027338624,
"min": 229.5838761627674,
"max": 2555.7194430828094,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.776118955191444,
"min": 1.8665355785590847,
"max": 3.953741100735552,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2118.4027338624,
"min": 229.5838761627674,
"max": 2555.7194430828094,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01706729011881786,
"min": 0.01406042383047558,
"max": 0.020156440096131215,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051201870356453585,
"min": 0.02812084766095116,
"max": 0.056431776310394824,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05645815216832691,
"min": 0.021196152611325188,
"max": 0.066980357033511,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16937445650498073,
"min": 0.042392305222650375,
"max": 0.1855288734038671,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.863548712183335e-06,
"min": 3.863548712183335e-06,
"max": 0.00029533980155339987,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1590646136550007e-05,
"min": 1.1590646136550007e-05,
"max": 0.0008441025186324998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128781666666668,
"min": 0.10128781666666668,
"max": 0.19844660000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30386345000000003,
"min": 0.20770315,
"max": 0.5813674999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.42620516666667e-05,
"min": 7.42620516666667e-05,
"max": 0.00492248534,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002227861550000001,
"min": 0.0002227861550000001,
"max": 0.014070238249999999,
"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": "1767204726",
"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=Huggy --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": "1767207297"
},
"total": 2571.612202975,
"count": 1,
"self": 0.421983457999886,
"children": {
"run_training.setup": {
"total": 0.02661433800000168,
"count": 1,
"self": 0.02661433800000168
},
"TrainerController.start_learning": {
"total": 2571.163605179,
"count": 1,
"self": 4.256762098959371,
"children": {
"TrainerController._reset_env": {
"total": 2.737217332,
"count": 1,
"self": 2.737217332
},
"TrainerController.advance": {
"total": 2564.071730611041,
"count": 233171,
"self": 4.508314466133925,
"children": {
"env_step": {
"total": 2093.7009559788985,
"count": 233171,
"self": 1692.017065526114,
"children": {
"SubprocessEnvManager._take_step": {
"total": 398.966772348859,
"count": 233171,
"self": 15.268934844881414,
"children": {
"TorchPolicy.evaluate": {
"total": 383.6978375039776,
"count": 222960,
"self": 383.6978375039776
}
}
},
"workers": {
"total": 2.7171181039253156,
"count": 233171,
"self": 0.0,
"children": {
"worker_root": {
"total": 2559.016248577915,
"count": 233171,
"is_parallel": true,
"self": 1186.4541147749228,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011662000000001171,
"count": 1,
"is_parallel": true,
"self": 0.0003722530000231927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007939469999769244,
"count": 2,
"is_parallel": true,
"self": 0.0007939469999769244
}
}
},
"UnityEnvironment.step": {
"total": 0.0310014840000008,
"count": 1,
"is_parallel": true,
"self": 0.0003314149999482652,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002013630000305966,
"count": 1,
"is_parallel": true,
"self": 0.0002013630000305966
},
"communicator.exchange": {
"total": 0.029719650000004094,
"count": 1,
"is_parallel": true,
"self": 0.029719650000004094
},
"steps_from_proto": {
"total": 0.0007490560000178448,
"count": 1,
"is_parallel": true,
"self": 0.00020446000002039,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005445959999974548,
"count": 2,
"is_parallel": true,
"self": 0.0005445959999974548
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1372.5621338029923,
"count": 233170,
"is_parallel": true,
"self": 38.692274972931955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.38738283710052,
"count": 233170,
"is_parallel": true,
"self": 84.38738283710052
},
"communicator.exchange": {
"total": 1159.0939300520172,
"count": 233170,
"is_parallel": true,
"self": 1159.0939300520172
},
"steps_from_proto": {
"total": 90.3885459409426,
"count": 233170,
"is_parallel": true,
"self": 32.31591817201763,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.072627768924974,
"count": 466340,
"is_parallel": true,
"self": 58.072627768924974
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 465.86246016600865,
"count": 233171,
"self": 6.437242285076707,
"children": {
"process_trajectory": {
"total": 159.60342246893242,
"count": 233171,
"self": 158.4916890109322,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1117334580002307,
"count": 10,
"self": 1.1117334580002307
}
}
},
"_update_policy": {
"total": 299.8217954119995,
"count": 97,
"self": 237.87739785499662,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.9443975570029,
"count": 2910,
"self": 61.9443975570029
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.059999683813658e-07,
"count": 1,
"self": 9.059999683813658e-07
},
"TrainerController._save_models": {
"total": 0.09789423099982741,
"count": 1,
"self": 0.0012245709999660903,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09666965999986132,
"count": 1,
"self": 0.09666965999986132
}
}
}
}
}
}
}