ppo-Huggy / run_logs /timers.json
JDB03's picture
Huggy first commit
17cc60a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066706895828247,
"min": 1.4066706895828247,
"max": 1.425573706626892,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71779.59375,
"min": 68170.4140625,
"max": 79063.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.85688405797102,
"min": 81.66231647634584,
"max": 427.79661016949154,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49601.0,
"min": 48751.0,
"max": 50480.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999831.0,
"min": 49848.0,
"max": 1999831.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999831.0,
"min": 49848.0,
"max": 1999831.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3790650367736816,
"min": -0.04980931803584099,
"max": 2.494490146636963,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1313.243896484375,
"min": -5.827690124511719,
"max": 1472.335693359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.605572000361871,
"min": 1.8260428248307643,
"max": 3.945180891520334,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1990.2757441997528,
"min": 213.64701050519943,
"max": 2301.7291192412376,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.605572000361871,
"min": 1.8260428248307643,
"max": 3.945180891520334,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1990.2757441997528,
"min": 213.64701050519943,
"max": 2301.7291192412376,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014801619388486467,
"min": 0.01297566265173676,
"max": 0.02070119214347667,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0444048581654594,
"min": 0.02595132530347352,
"max": 0.06210357643043002,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04756907501982318,
"min": 0.022106212098151445,
"max": 0.060032101265258264,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14270722505946953,
"min": 0.04421242419630289,
"max": 0.1800963037957748,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.297148900983336e-06,
"min": 3.297148900983336e-06,
"max": 0.00029530515156495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.891446702950008e-06,
"min": 9.891446702950008e-06,
"max": 0.0008438811187062999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109901666666665,
"min": 0.10109901666666665,
"max": 0.19843504999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30329704999999996,
"min": 0.2073679,
"max": 0.5812937,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.484093166666669e-05,
"min": 6.484093166666669e-05,
"max": 0.004921908995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019452279500000008,
"min": 0.00019452279500000008,
"max": 0.014066555630000002,
"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": "1704757436",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704760192"
},
"total": 2755.8728281539998,
"count": 1,
"self": 0.4378827829996226,
"children": {
"run_training.setup": {
"total": 0.049662721999993664,
"count": 1,
"self": 0.049662721999993664
},
"TrainerController.start_learning": {
"total": 2755.385282649,
"count": 1,
"self": 5.759890625023218,
"children": {
"TrainerController._reset_env": {
"total": 3.112585619000015,
"count": 1,
"self": 3.112585619000015
},
"TrainerController.advance": {
"total": 2746.3870301209768,
"count": 232616,
"self": 5.531001716919036,
"children": {
"env_step": {
"total": 2212.8514908900643,
"count": 232616,
"self": 1835.9438600980102,
"children": {
"SubprocessEnvManager._take_step": {
"total": 373.1109103089723,
"count": 232616,
"self": 19.821656008852983,
"children": {
"TorchPolicy.evaluate": {
"total": 353.2892543001193,
"count": 223060,
"self": 353.2892543001193
}
}
},
"workers": {
"total": 3.796720483081799,
"count": 232616,
"self": 0.0,
"children": {
"worker_root": {
"total": 2746.56331663389,
"count": 232616,
"is_parallel": true,
"self": 1256.524714769881,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006733489999533049,
"count": 1,
"is_parallel": true,
"self": 0.00019092399986675446,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004824250000865504,
"count": 2,
"is_parallel": true,
"self": 0.0004824250000865504
}
}
},
"UnityEnvironment.step": {
"total": 0.030875410000021475,
"count": 1,
"is_parallel": true,
"self": 0.00032878100012112554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019013199994333263,
"count": 1,
"is_parallel": true,
"self": 0.00019013199994333263
},
"communicator.exchange": {
"total": 0.02960670899994966,
"count": 1,
"is_parallel": true,
"self": 0.02960670899994966
},
"steps_from_proto": {
"total": 0.0007497880000073565,
"count": 1,
"is_parallel": true,
"self": 0.00020429599999260972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005454920000147467,
"count": 2,
"is_parallel": true,
"self": 0.0005454920000147467
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1490.0386018640088,
"count": 232615,
"is_parallel": true,
"self": 45.453026697035284,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.68253253693592,
"count": 232615,
"is_parallel": true,
"self": 92.68253253693592
},
"communicator.exchange": {
"total": 1248.0425220330408,
"count": 232615,
"is_parallel": true,
"self": 1248.0425220330408
},
"steps_from_proto": {
"total": 103.86052059699682,
"count": 232615,
"is_parallel": true,
"self": 36.031917224962285,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.82860337203454,
"count": 465230,
"is_parallel": true,
"self": 67.82860337203454
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.0045375139932,
"count": 232616,
"self": 9.07291212396467,
"children": {
"process_trajectory": {
"total": 170.71773336002843,
"count": 232616,
"self": 169.45428579102793,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2634475690005047,
"count": 10,
"self": 1.2634475690005047
}
}
},
"_update_policy": {
"total": 348.2138920300001,
"count": 97,
"self": 280.55195518299047,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.66193684700966,
"count": 2910,
"self": 67.66193684700966
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.079999472305644e-07,
"count": 1,
"self": 9.079999472305644e-07
},
"TrainerController._save_models": {
"total": 0.12577537600009236,
"count": 1,
"self": 0.00215639399993961,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12361898200015276,
"count": 1,
"self": 0.12361898200015276
}
}
}
}
}
}
}