ppo-Huggy / run_logs /timers.json
gork-projects's picture
Huggy
6f868fb verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405526041984558,
"min": 1.405526041984558,
"max": 1.429772973060608,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68189.09375,
"min": 68189.09375,
"max": 77171.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.65767634854772,
"min": 84.88850174216027,
"max": 366.55474452554745,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49481.0,
"min": 48726.0,
"max": 50218.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999910.0,
"min": 49720.0,
"max": 1999910.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999910.0,
"min": 49720.0,
"max": 1999910.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3742027282714844,
"min": 0.0319172739982605,
"max": 2.47392201423645,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1144.36572265625,
"min": 4.340749263763428,
"max": 1399.26513671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6567965744689293,
"min": 1.8376562647959764,
"max": 3.9508272752752895,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1762.575948894024,
"min": 249.9212520122528,
"max": 2165.4050627350807,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6567965744689293,
"min": 1.8376562647959764,
"max": 3.9508272752752895,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1762.575948894024,
"min": 249.9212520122528,
"max": 2165.4050627350807,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017163515745778568,
"min": 0.012869175925475753,
"max": 0.018874677662582447,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051490547237335704,
"min": 0.028122005405991028,
"max": 0.05520011600819998,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05345268435776233,
"min": 0.02287174335991343,
"max": 0.06151694214592377,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.160358053073287,
"min": 0.04574348671982686,
"max": 0.17889239229261875,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.457348847583333e-06,
"min": 3.457348847583333e-06,
"max": 0.00029532795155734996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0372046542749999e-05,
"min": 1.0372046542749999e-05,
"max": 0.00084398956867015,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115241666666668,
"min": 0.10115241666666668,
"max": 0.19844265,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30345725,
"min": 0.20742924999999995,
"max": 0.5813298499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.750559166666665e-05,
"min": 6.750559166666665e-05,
"max": 0.004922288235,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020251677499999996,
"min": 0.00020251677499999996,
"max": 0.014068359515,
"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": "1749448268",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749450797"
},
"total": 2528.738209361,
"count": 1,
"self": 0.43939255100031005,
"children": {
"run_training.setup": {
"total": 0.02244671800008291,
"count": 1,
"self": 0.02244671800008291
},
"TrainerController.start_learning": {
"total": 2528.2763700919995,
"count": 1,
"self": 4.6697863778158535,
"children": {
"TrainerController._reset_env": {
"total": 3.2644318309999107,
"count": 1,
"self": 3.2644318309999107
},
"TrainerController.advance": {
"total": 2520.235982592185,
"count": 232067,
"self": 4.915938708263184,
"children": {
"env_step": {
"total": 2024.580865703958,
"count": 232067,
"self": 1596.108725932117,
"children": {
"SubprocessEnvManager._take_step": {
"total": 425.7716607809821,
"count": 232067,
"self": 16.057953072168402,
"children": {
"TorchPolicy.evaluate": {
"total": 409.7137077088137,
"count": 222960,
"self": 409.7137077088137
}
}
},
"workers": {
"total": 2.7004789908587554,
"count": 232067,
"self": 0.0,
"children": {
"worker_root": {
"total": 2520.672221495841,
"count": 232067,
"is_parallel": true,
"self": 1220.6525533899298,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011359999998603598,
"count": 1,
"is_parallel": true,
"self": 0.00029236599993964774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008436339999207121,
"count": 2,
"is_parallel": true,
"self": 0.0008436339999207121
}
}
},
"UnityEnvironment.step": {
"total": 0.04760576999979094,
"count": 1,
"is_parallel": true,
"self": 0.0003535179998834792,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001901599998745951,
"count": 1,
"is_parallel": true,
"self": 0.0001901599998745951
},
"communicator.exchange": {
"total": 0.046349487000043155,
"count": 1,
"is_parallel": true,
"self": 0.046349487000043155
},
"steps_from_proto": {
"total": 0.0007126049999897077,
"count": 1,
"is_parallel": true,
"self": 0.0002225439993708278,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004900610006188799,
"count": 2,
"is_parallel": true,
"self": 0.0004900610006188799
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1300.019668105911,
"count": 232066,
"is_parallel": true,
"self": 37.94321765997256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.86911176112335,
"count": 232066,
"is_parallel": true,
"self": 84.86911176112335
},
"communicator.exchange": {
"total": 1087.2550495660075,
"count": 232066,
"is_parallel": true,
"self": 1087.2550495660075
},
"steps_from_proto": {
"total": 89.95228911880758,
"count": 232066,
"is_parallel": true,
"self": 33.40379676066004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.54849235814754,
"count": 464132,
"is_parallel": true,
"self": 56.54849235814754
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 490.7391781799638,
"count": 232067,
"self": 6.8408531799691445,
"children": {
"process_trajectory": {
"total": 169.7337671049945,
"count": 232067,
"self": 168.28148982399443,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4522772810000788,
"count": 10,
"self": 1.4522772810000788
}
}
},
"_update_policy": {
"total": 314.16455789500014,
"count": 97,
"self": 249.46645219499078,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.69810570000936,
"count": 2910,
"self": 64.69810570000936
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.919995136442594e-07,
"count": 1,
"self": 9.919995136442594e-07
},
"TrainerController._save_models": {
"total": 0.1061682989993642,
"count": 1,
"self": 0.00156897599936201,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10459932300000219,
"count": 1,
"self": 0.10459932300000219
}
}
}
}
}
}
}