ppo-Huggy / run_logs /timers.json
Shore02's picture
Upload 30 files
2ef7fa1 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046286344528198,
"min": 1.4046286344528198,
"max": 1.4232842922210693,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69551.59375,
"min": 68972.1484375,
"max": 77967.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.46725663716815,
"min": 75.89247311827957,
"max": 386.9612403100775,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49419.0,
"min": 48695.0,
"max": 50029.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999918.0,
"min": 49779.0,
"max": 1999918.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999918.0,
"min": 49779.0,
"max": 1999918.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.450911283493042,
"min": 0.11230558902025223,
"max": 2.5211522579193115,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1384.764892578125,
"min": 14.599726676940918,
"max": 1613.567626953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.762405700071723,
"min": 1.8667233013189757,
"max": 4.095319946098328,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2125.7592205405235,
"min": 242.67402917146683,
"max": 2559.574966311455,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.762405700071723,
"min": 1.8667233013189757,
"max": 4.095319946098328,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2125.7592205405235,
"min": 242.67402917146683,
"max": 2559.574966311455,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013524358704550347,
"min": 0.013524358704550347,
"max": 0.019515308752549268,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04057307611365104,
"min": 0.027152062762130905,
"max": 0.058545926257647804,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05367965536812941,
"min": 0.022565405815839767,
"max": 0.06356420545942253,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16103896610438823,
"min": 0.045130811631679535,
"max": 0.1906926163782676,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.948598683833332e-06,
"min": 3.948598683833332e-06,
"max": 0.0002953666515444501,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1845796051499998e-05,
"min": 1.1845796051499998e-05,
"max": 0.0008442085685971498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1013161666666667,
"min": 0.1013161666666667,
"max": 0.19845555000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30394850000000007,
"min": 0.20777275000000006,
"max": 0.58140285,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.567671666666664e-05,
"min": 7.567671666666664e-05,
"max": 0.004922931945,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022703014999999994,
"min": 0.00022703014999999994,
"max": 0.014072002215,
"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": "1761643690",
"python_version": "3.10.19 | packaged by conda-forge | (main, Oct 22 2025, 22:29:10) [GCC 14.3.0]",
"command_line_arguments": "/home/shore/miniconda3/envs/robocoin/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1761644669"
},
"total": 978.8648321599903,
"count": 1,
"self": 0.21738370598177426,
"children": {
"run_training.setup": {
"total": 0.01520541901118122,
"count": 1,
"self": 0.01520541901118122
},
"TrainerController.start_learning": {
"total": 978.6322430349974,
"count": 1,
"self": 2.6548341430170694,
"children": {
"TrainerController._reset_env": {
"total": 1.0513102200056892,
"count": 1,
"self": 1.0513102200056892
},
"TrainerController.advance": {
"total": 974.876166240967,
"count": 233214,
"self": 2.4534530339442426,
"children": {
"env_step": {
"total": 756.6072918600839,
"count": 233214,
"self": 557.9749261106481,
"children": {
"SubprocessEnvManager._take_step": {
"total": 196.8763146113779,
"count": 233214,
"self": 8.857910867780447,
"children": {
"TorchPolicy.evaluate": {
"total": 188.01840374359745,
"count": 223038,
"self": 188.01840374359745
}
}
},
"workers": {
"total": 1.7560511380579555,
"count": 233214,
"self": 0.0,
"children": {
"worker_root": {
"total": 975.8212335586868,
"count": 233214,
"is_parallel": true,
"self": 542.6536563649715,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00034322700230404735,
"count": 1,
"is_parallel": true,
"self": 8.672899275552481e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00025649800954852253,
"count": 2,
"is_parallel": true,
"self": 0.00025649800954852253
}
}
},
"UnityEnvironment.step": {
"total": 0.010456167001393624,
"count": 1,
"is_parallel": true,
"self": 0.00010225000733043998,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.697599696461111e-05,
"count": 1,
"is_parallel": true,
"self": 8.697599696461111e-05
},
"communicator.exchange": {
"total": 0.010032605001470074,
"count": 1,
"is_parallel": true,
"self": 0.010032605001470074
},
"steps_from_proto": {
"total": 0.0002343359956284985,
"count": 1,
"is_parallel": true,
"self": 6.40359940007329e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0001703000016277656,
"count": 2,
"is_parallel": true,
"self": 0.0001703000016277656
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 433.16757719371526,
"count": 233213,
"is_parallel": true,
"self": 13.114813022184535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.465928697027266,
"count": 233213,
"is_parallel": true,
"self": 23.465928697027266
},
"communicator.exchange": {
"total": 366.83239913964644,
"count": 233213,
"is_parallel": true,
"self": 366.83239913964644
},
"steps_from_proto": {
"total": 29.75443633485702,
"count": 233213,
"is_parallel": true,
"self": 9.784856316196965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 19.969580018660054,
"count": 466426,
"is_parallel": true,
"self": 19.969580018660054
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 215.81542134693882,
"count": 233214,
"self": 3.8370741109829396,
"children": {
"process_trajectory": {
"total": 81.17846244898101,
"count": 233214,
"self": 80.50399969899445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6744627499865601,
"count": 10,
"self": 0.6744627499865601
}
}
},
"_update_policy": {
"total": 130.79988478697487,
"count": 97,
"self": 106.06500991810753,
"children": {
"TorchPPOOptimizer.update": {
"total": 24.734874868867337,
"count": 2910,
"self": 24.734874868867337
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.760076990351081e-07,
"count": 1,
"self": 4.760076990351081e-07
},
"TrainerController._save_models": {
"total": 0.04993195499991998,
"count": 1,
"self": 0.001221789003466256,
"children": {
"RLTrainer._checkpoint": {
"total": 0.048710165996453725,
"count": 1,
"self": 0.048710165996453725
}
}
}
}
}
}
}