ppo-Huggy / run_logs /timers.json
arekpaterak's picture
Huggy
8ccadd8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407570481300354,
"min": 1.407570481300354,
"max": 1.427304983139038,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71341.3046875,
"min": 68309.1484375,
"max": 77333.8671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.55579868708972,
"min": 89.88990825688073,
"max": 378.25563909774434,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49610.0,
"min": 48990.0,
"max": 50308.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49879.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49879.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3637046813964844,
"min": 0.08151707053184509,
"max": 2.424647092819214,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1077.849365234375,
"min": 10.760252952575684,
"max": 1321.4326171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.662831139276948,
"min": 1.7019522549076513,
"max": 3.8422797380362526,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1670.2509995102882,
"min": 224.65769764780998,
"max": 2043.1068328022957,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.662831139276948,
"min": 1.7019522549076513,
"max": 3.8422797380362526,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1670.2509995102882,
"min": 224.65769764780998,
"max": 2043.1068328022957,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01928647763561457,
"min": 0.013963028891400123,
"max": 0.020225021743681282,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03857295527122914,
"min": 0.027926057782800245,
"max": 0.060675065231043844,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.046206396507720154,
"min": 0.02059100102633238,
"max": 0.05689422003924847,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09241279301544031,
"min": 0.04118200205266476,
"max": 0.1706826601177454,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.608248463949998e-06,
"min": 4.608248463949998e-06,
"max": 0.0002953695015434999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.216496927899996e-06,
"min": 9.216496927899996e-06,
"max": 0.0008441001186332998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153605,
"min": 0.10153605,
"max": 0.19845650000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2030721,
"min": 0.2030721,
"max": 0.5813667000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.664889500000003e-05,
"min": 8.664889500000003e-05,
"max": 0.00492297935,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017329779000000006,
"min": 0.00017329779000000006,
"max": 0.014070198329999999,
"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": "1708182395",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708184691"
},
"total": 2295.256777151,
"count": 1,
"self": 0.47550224499946125,
"children": {
"run_training.setup": {
"total": 0.05051368900001307,
"count": 1,
"self": 0.05051368900001307
},
"TrainerController.start_learning": {
"total": 2294.7307612170002,
"count": 1,
"self": 4.378376588044375,
"children": {
"TrainerController._reset_env": {
"total": 2.2412716200000204,
"count": 1,
"self": 2.2412716200000204
},
"TrainerController.advance": {
"total": 2287.995946600956,
"count": 231583,
"self": 4.478963573970759,
"children": {
"env_step": {
"total": 1813.7341813069954,
"count": 231583,
"self": 1493.5101185819913,
"children": {
"SubprocessEnvManager._take_step": {
"total": 317.46908551397314,
"count": 231583,
"self": 16.853809638053235,
"children": {
"TorchPolicy.evaluate": {
"total": 300.6152758759199,
"count": 223046,
"self": 300.6152758759199
}
}
},
"workers": {
"total": 2.754977211030905,
"count": 231583,
"self": 0.0,
"children": {
"worker_root": {
"total": 2287.5527959298543,
"count": 231583,
"is_parallel": true,
"self": 1067.5687998588182,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009082650000209469,
"count": 1,
"is_parallel": true,
"self": 0.00023071800001162046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006775470000093264,
"count": 2,
"is_parallel": true,
"self": 0.0006775470000093264
}
}
},
"UnityEnvironment.step": {
"total": 0.029150140999945506,
"count": 1,
"is_parallel": true,
"self": 0.0002815269999700831,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024133299996265123,
"count": 1,
"is_parallel": true,
"self": 0.00024133299996265123
},
"communicator.exchange": {
"total": 0.027894643999957225,
"count": 1,
"is_parallel": true,
"self": 0.027894643999957225
},
"steps_from_proto": {
"total": 0.0007326370000555471,
"count": 1,
"is_parallel": true,
"self": 0.00019761600015044678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005350209999051003,
"count": 2,
"is_parallel": true,
"self": 0.0005350209999051003
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1219.983996071036,
"count": 231582,
"is_parallel": true,
"self": 39.41567313395876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.95976821004979,
"count": 231582,
"is_parallel": true,
"self": 79.95976821004979
},
"communicator.exchange": {
"total": 1012.7670873120771,
"count": 231582,
"is_parallel": true,
"self": 1012.7670873120771
},
"steps_from_proto": {
"total": 87.84146741495033,
"count": 231582,
"is_parallel": true,
"self": 30.900832579917733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.9406348350326,
"count": 463164,
"is_parallel": true,
"self": 56.9406348350326
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 469.7828017199896,
"count": 231583,
"self": 6.388259938113379,
"children": {
"process_trajectory": {
"total": 139.9362333988738,
"count": 231583,
"self": 138.7565357818736,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1796976170002154,
"count": 10,
"self": 1.1796976170002154
}
}
},
"_update_policy": {
"total": 323.4583083830024,
"count": 96,
"self": 260.4415273659921,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.01678101701032,
"count": 2880,
"self": 63.01678101701032
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.213999894389417e-06,
"count": 1,
"self": 1.213999894389417e-06
},
"TrainerController._save_models": {
"total": 0.1151651939999283,
"count": 1,
"self": 0.0018565669997769874,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11330862700015132,
"count": 1,
"self": 0.11330862700015132
}
}
}
}
}
}
}