ppo-Huggy / run_logs /timers.json
LeoCAv's picture
Huggy
2ef4889 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037705659866333,
"min": 1.4037705659866333,
"max": 1.4255346059799194,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71748.1171875,
"min": 67938.7578125,
"max": 76571.4609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.168458781362,
"min": 86.23157894736842,
"max": 405.008064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49756.0,
"min": 49104.0,
"max": 50221.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999578.0,
"min": 49923.0,
"max": 1999578.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999578.0,
"min": 49923.0,
"max": 1999578.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.43213152885437,
"min": 0.21694748103618622,
"max": 2.5050864219665527,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1357.12939453125,
"min": 26.684539794921875,
"max": 1407.02197265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8660758924954255,
"min": 1.9161605560561505,
"max": 4.03408555865736,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2157.2703480124474,
"min": 235.68774839490652,
"max": 2220.8679201602936,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8660758924954255,
"min": 1.9161605560561505,
"max": 4.03408555865736,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2157.2703480124474,
"min": 235.68774839490652,
"max": 2220.8679201602936,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016030152033312737,
"min": 0.01452963159083285,
"max": 0.020419074154536553,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048090456099938214,
"min": 0.030384356439268838,
"max": 0.05613342119177105,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05532080791890622,
"min": 0.020280961847553652,
"max": 0.0600253161870771,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16596242375671866,
"min": 0.040561923695107305,
"max": 0.1800759485612313,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2324989225333356e-06,
"min": 3.2324989225333356e-06,
"max": 0.00029537272654242504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.697496767600007e-06,
"min": 9.697496767600007e-06,
"max": 0.0008442745685751499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107746666666668,
"min": 0.10107746666666668,
"max": 0.198457575,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30323240000000007,
"min": 0.20730835,
"max": 0.5814248500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.37655866666667e-05,
"min": 6.37655866666667e-05,
"max": 0.004923032992499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019129676000000011,
"min": 0.00019129676000000011,
"max": 0.014073100015000003,
"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": "1739833178",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739835630"
},
"total": 2451.473990366,
"count": 1,
"self": 0.4367752460002521,
"children": {
"run_training.setup": {
"total": 0.022991685999954825,
"count": 1,
"self": 0.022991685999954825
},
"TrainerController.start_learning": {
"total": 2451.014223434,
"count": 1,
"self": 4.428750069967009,
"children": {
"TrainerController._reset_env": {
"total": 2.998101868000049,
"count": 1,
"self": 2.998101868000049
},
"TrainerController.advance": {
"total": 2443.473680675033,
"count": 232289,
"self": 4.849694834112142,
"children": {
"env_step": {
"total": 1962.5386280329296,
"count": 232289,
"self": 1537.859160863941,
"children": {
"SubprocessEnvManager._take_step": {
"total": 422.03619173994707,
"count": 232289,
"self": 15.902823851976791,
"children": {
"TorchPolicy.evaluate": {
"total": 406.1333678879703,
"count": 223007,
"self": 406.1333678879703
}
}
},
"workers": {
"total": 2.6432754290415232,
"count": 232289,
"self": 0.0,
"children": {
"worker_root": {
"total": 2443.3427344750967,
"count": 232289,
"is_parallel": true,
"self": 1190.5795408821184,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009666379999089258,
"count": 1,
"is_parallel": true,
"self": 0.00027394299991101434,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006926949999979115,
"count": 2,
"is_parallel": true,
"self": 0.0006926949999979115
}
}
},
"UnityEnvironment.step": {
"total": 0.029888815000049362,
"count": 1,
"is_parallel": true,
"self": 0.0002889450001930527,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018005900005846343,
"count": 1,
"is_parallel": true,
"self": 0.00018005900005846343
},
"communicator.exchange": {
"total": 0.028560318999780065,
"count": 1,
"is_parallel": true,
"self": 0.028560318999780065
},
"steps_from_proto": {
"total": 0.0008594920000177808,
"count": 1,
"is_parallel": true,
"self": 0.00019084799987467704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006686440001431038,
"count": 2,
"is_parallel": true,
"self": 0.0006686440001431038
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1252.7631935929783,
"count": 232288,
"is_parallel": true,
"self": 36.87904197908074,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.43922082591666,
"count": 232288,
"is_parallel": true,
"self": 82.43922082591666
},
"communicator.exchange": {
"total": 1045.53135661395,
"count": 232288,
"is_parallel": true,
"self": 1045.53135661395
},
"steps_from_proto": {
"total": 87.91357417403083,
"count": 232288,
"is_parallel": true,
"self": 32.88921089910309,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.02436327492774,
"count": 464576,
"is_parallel": true,
"self": 55.02436327492774
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.08535780799116,
"count": 232289,
"self": 6.495620569968651,
"children": {
"process_trajectory": {
"total": 162.90774945002204,
"count": 232289,
"self": 161.53816259002247,
"children": {
"RLTrainer._checkpoint": {
"total": 1.369586859999572,
"count": 10,
"self": 1.369586859999572
}
}
},
"_update_policy": {
"total": 306.68198778800047,
"count": 97,
"self": 242.98365062399625,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.698337164004215,
"count": 2910,
"self": 63.698337164004215
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.679999154992402e-07,
"count": 1,
"self": 8.679999154992402e-07
},
"TrainerController._save_models": {
"total": 0.11368995300017559,
"count": 1,
"self": 0.001838541000324767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11185141199985082,
"count": 1,
"self": 0.11185141199985082
}
}
}
}
}
}
}