ppo-Huggy / run_logs /timers.json
kate0711's picture
Huggy
0c28913 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100220203399658,
"min": 1.4100220203399658,
"max": 1.427291989326477,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71428.8984375,
"min": 68726.5,
"max": 76086.421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.16206896551724,
"min": 85.16206896551724,
"max": 390.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49394.0,
"min": 48972.0,
"max": 50032.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999968.0,
"min": 49594.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999968.0,
"min": 49594.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3501803874969482,
"min": 0.021051717922091484,
"max": 2.4164323806762695,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1363.1046142578125,
"min": 2.6735682487487793,
"max": 1363.1046142578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.623640402843212,
"min": 1.7746333846543718,
"max": 3.941196617152956,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2101.711433649063,
"min": 225.3784398511052,
"max": 2101.711433649063,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.623640402843212,
"min": 1.7746333846543718,
"max": 3.941196617152956,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2101.711433649063,
"min": 225.3784398511052,
"max": 2101.711433649063,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015922308701556177,
"min": 0.01376679201036192,
"max": 0.02079355275685278,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04776692610466853,
"min": 0.02753358402072384,
"max": 0.05950522249719749,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05401323495639695,
"min": 0.023789196213086446,
"max": 0.05689189446469148,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16203970486919084,
"min": 0.04757839242617289,
"max": 0.16805730871856212,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.499398833566672e-06,
"min": 3.499398833566672e-06,
"max": 0.00029532735155754996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0498196500700016e-05,
"min": 1.0498196500700016e-05,
"max": 0.0008441943186019,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116643333333335,
"min": 0.10116643333333335,
"max": 0.19844245,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034993,
"min": 0.20749735000000002,
"max": 0.5813981000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.820502333333341e-05,
"min": 6.820502333333341e-05,
"max": 0.004922278255,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020461507000000024,
"min": 0.00020461507000000024,
"max": 0.01407176519,
"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": "1739253352",
"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": "1739255831"
},
"total": 2479.469671579,
"count": 1,
"self": 0.660251702000096,
"children": {
"run_training.setup": {
"total": 0.029018833999998606,
"count": 1,
"self": 0.029018833999998606
},
"TrainerController.start_learning": {
"total": 2478.780401043,
"count": 1,
"self": 4.4657754750269305,
"children": {
"TrainerController._reset_env": {
"total": 3.1536988410000504,
"count": 1,
"self": 3.1536988410000504
},
"TrainerController.advance": {
"total": 2470.980623896973,
"count": 232105,
"self": 4.660099440812701,
"children": {
"env_step": {
"total": 1970.015561282113,
"count": 232105,
"self": 1546.898194567993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 420.4398383480874,
"count": 232105,
"self": 16.079508491198,
"children": {
"TorchPolicy.evaluate": {
"total": 404.3603298568894,
"count": 222988,
"self": 404.3603298568894
}
}
},
"workers": {
"total": 2.6775283660324476,
"count": 232105,
"self": 0.0,
"children": {
"worker_root": {
"total": 2471.1412185409226,
"count": 232105,
"is_parallel": true,
"self": 1206.2899180538477,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010028760000295733,
"count": 1,
"is_parallel": true,
"self": 0.0003606000000218046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006422760000077687,
"count": 2,
"is_parallel": true,
"self": 0.0006422760000077687
}
}
},
"UnityEnvironment.step": {
"total": 0.029739811000013106,
"count": 1,
"is_parallel": true,
"self": 0.00030629599996245815,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021046500000920787,
"count": 1,
"is_parallel": true,
"self": 0.00021046500000920787
},
"communicator.exchange": {
"total": 0.02852403199995024,
"count": 1,
"is_parallel": true,
"self": 0.02852403199995024
},
"steps_from_proto": {
"total": 0.0006990180000912005,
"count": 1,
"is_parallel": true,
"self": 0.00019551900004444178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005034990000467587,
"count": 2,
"is_parallel": true,
"self": 0.0005034990000467587
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1264.851300487075,
"count": 232104,
"is_parallel": true,
"self": 37.8503967150059,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.3764580629819,
"count": 232104,
"is_parallel": true,
"self": 82.3764580629819
},
"communicator.exchange": {
"total": 1056.954380726079,
"count": 232104,
"is_parallel": true,
"self": 1056.954380726079
},
"steps_from_proto": {
"total": 87.67006498300793,
"count": 232104,
"is_parallel": true,
"self": 32.261914946776756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.40815003623118,
"count": 464208,
"is_parallel": true,
"self": 55.40815003623118
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 496.30496317404777,
"count": 232105,
"self": 6.499773119013639,
"children": {
"process_trajectory": {
"total": 163.57864443503445,
"count": 232105,
"self": 162.19508440703453,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3835600279999198,
"count": 10,
"self": 1.3835600279999198
}
}
},
"_update_policy": {
"total": 326.2265456199997,
"count": 97,
"self": 261.3533040300073,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.8732415899924,
"count": 2910,
"self": 64.8732415899924
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2489999789977446e-06,
"count": 1,
"self": 1.2489999789977446e-06
},
"TrainerController._save_models": {
"total": 0.1803015810000943,
"count": 1,
"self": 0.0035500240001056227,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17675155699998868,
"count": 1,
"self": 0.17675155699998868
}
}
}
}
}
}
}