ppo-Huggy / run_logs /timers.json
fangwch's picture
Huggy
7d02391 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4019662141799927,
"min": 1.4019662141799927,
"max": 1.4276454448699951,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69959.515625,
"min": 68022.8203125,
"max": 78805.140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.42143906020559,
"min": 70.43428571428572,
"max": 386.4153846153846,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49319.0,
"min": 49035.0,
"max": 50234.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49901.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49901.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5078279972076416,
"min": 0.1392013430595398,
"max": 2.540672540664673,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1707.830810546875,
"min": 17.956974029541016,
"max": 1773.389404296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8749957226446545,
"min": 1.8265752161658086,
"max": 4.083782497955405,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2638.87208712101,
"min": 235.62820288538933,
"max": 2786.100259542465,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8749957226446545,
"min": 1.8265752161658086,
"max": 4.083782497955405,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2638.87208712101,
"min": 235.62820288538933,
"max": 2786.100259542465,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01725803627729571,
"min": 0.0120378778870266,
"max": 0.019779625341955886,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051774108831887135,
"min": 0.0240757557740532,
"max": 0.059338876025867654,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06163429377807511,
"min": 0.023297961428761484,
"max": 0.06741565397630135,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18490288133422533,
"min": 0.04659592285752297,
"max": 0.19086526930332187,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.871948709383332e-06,
"min": 3.871948709383332e-06,
"max": 0.00029528947657017504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1615846128149997e-05,
"min": 1.1615846128149997e-05,
"max": 0.0008437996687334498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129061666666667,
"min": 0.10129061666666667,
"max": 0.19842982500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30387185,
"min": 0.20771514999999996,
"max": 0.58126655,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.440177166666665e-05,
"min": 7.440177166666665e-05,
"max": 0.0049216482674999985,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022320531499999996,
"min": 0.00022320531499999996,
"max": 0.014065200845000002,
"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": "1751873631",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/envs/myenv/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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751876140"
},
"total": 2509.657437461,
"count": 1,
"self": 0.6904651940003532,
"children": {
"run_training.setup": {
"total": 0.017820289000155753,
"count": 1,
"self": 0.017820289000155753
},
"TrainerController.start_learning": {
"total": 2508.9491519779995,
"count": 1,
"self": 4.227231101931466,
"children": {
"TrainerController._reset_env": {
"total": 3.046077920999778,
"count": 1,
"self": 3.046077920999778
},
"TrainerController.advance": {
"total": 2501.5153117070686,
"count": 233555,
"self": 4.335791830334529,
"children": {
"env_step": {
"total": 2002.1873224509927,
"count": 233555,
"self": 1592.2072504793105,
"children": {
"SubprocessEnvManager._take_step": {
"total": 407.2835850690126,
"count": 233555,
"self": 15.301025071998083,
"children": {
"TorchPolicy.evaluate": {
"total": 391.9825599970145,
"count": 222927,
"self": 391.9825599970145
}
}
},
"workers": {
"total": 2.696486902669676,
"count": 233555,
"self": 0.0,
"children": {
"worker_root": {
"total": 2501.374198519705,
"count": 233555,
"is_parallel": true,
"self": 1204.047350357765,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009406010003658594,
"count": 1,
"is_parallel": true,
"self": 0.0002821550006046891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006584459997611702,
"count": 2,
"is_parallel": true,
"self": 0.0006584459997611702
}
}
},
"UnityEnvironment.step": {
"total": 0.02899327799968887,
"count": 1,
"is_parallel": true,
"self": 0.0003329979999762145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021274499977153027,
"count": 1,
"is_parallel": true,
"self": 0.00021274499977153027
},
"communicator.exchange": {
"total": 0.027771721999670262,
"count": 1,
"is_parallel": true,
"self": 0.027771721999670262
},
"steps_from_proto": {
"total": 0.000675813000270864,
"count": 1,
"is_parallel": true,
"self": 0.00018683600046642823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004889769998044358,
"count": 2,
"is_parallel": true,
"self": 0.0004889769998044358
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1297.3268481619398,
"count": 233554,
"is_parallel": true,
"self": 37.61748855364749,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.89666487315571,
"count": 233554,
"is_parallel": true,
"self": 83.89666487315571
},
"communicator.exchange": {
"total": 1086.2478311551922,
"count": 233554,
"is_parallel": true,
"self": 1086.2478311551922
},
"steps_from_proto": {
"total": 89.56486357994436,
"count": 233554,
"is_parallel": true,
"self": 33.24894916535504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.315914414589315,
"count": 467108,
"is_parallel": true,
"self": 56.315914414589315
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.9921974257413,
"count": 233555,
"self": 6.26780278377737,
"children": {
"process_trajectory": {
"total": 171.5922675889624,
"count": 233555,
"self": 170.2807416449632,
"children": {
"RLTrainer._checkpoint": {
"total": 1.311525943999186,
"count": 10,
"self": 1.311525943999186
}
}
},
"_update_policy": {
"total": 317.13212705300157,
"count": 97,
"self": 256.37978530099554,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.75234175200603,
"count": 2910,
"self": 60.75234175200603
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3669996405951679e-06,
"count": 1,
"self": 1.3669996405951679e-06
},
"TrainerController._save_models": {
"total": 0.1605298810000022,
"count": 1,
"self": 0.0023115829999369453,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15821829800006526,
"count": 1,
"self": 0.15821829800006526
}
}
}
}
}
}
}