ppo-Huggy / run_logs /timers.json
SamFic's picture
Huggy
7008575 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407077670097351,
"min": 1.407077670097351,
"max": 1.4268382787704468,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70735.203125,
"min": 69128.2109375,
"max": 77784.4296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.74503311258277,
"min": 78.76837060702876,
"max": 381.4351145038168,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49374.0,
"min": 49112.0,
"max": 49970.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49909.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49909.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.428349494934082,
"min": 0.2009531855583191,
"max": 2.4600555896759033,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1466.72314453125,
"min": 26.12391471862793,
"max": 1521.43994140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.82238270559453,
"min": 1.8897378174158244,
"max": 4.061696049912834,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2308.719154179096,
"min": 245.66591626405716,
"max": 2400.3398638367653,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.82238270559453,
"min": 1.8897378174158244,
"max": 4.061696049912834,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2308.719154179096,
"min": 245.66591626405716,
"max": 2400.3398638367653,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015050642206875233,
"min": 0.014024211932943825,
"max": 0.021274792200226024,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0451519266206257,
"min": 0.02804842386588765,
"max": 0.05726967878678503,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05823669160405795,
"min": 0.020873983887334663,
"max": 0.0620793425788482,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17471007481217385,
"min": 0.041747967774669326,
"max": 0.17471007481217385,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.451298849599999e-06,
"min": 3.451298849599999e-06,
"max": 0.000295351876549375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0353896548799997e-05,
"min": 1.0353896548799997e-05,
"max": 0.0008441953686015501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115039999999999,
"min": 0.10115039999999999,
"max": 0.198450625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034512,
"min": 0.20747295000000004,
"max": 0.58139845,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.740495999999998e-05,
"min": 6.740495999999998e-05,
"max": 0.004922686187500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020221487999999994,
"min": 0.00020221487999999994,
"max": 0.014071782655,
"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": "1754501054",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1754503451"
},
"total": 2396.970742406,
"count": 1,
"self": 0.453614215000016,
"children": {
"run_training.setup": {
"total": 0.03111361700030102,
"count": 1,
"self": 0.03111361700030102
},
"TrainerController.start_learning": {
"total": 2396.486014574,
"count": 1,
"self": 3.9388861782363165,
"children": {
"TrainerController._reset_env": {
"total": 3.3389841979997072,
"count": 1,
"self": 3.3389841979997072
},
"TrainerController.advance": {
"total": 2389.109174562765,
"count": 232548,
"self": 4.056940687766655,
"children": {
"env_step": {
"total": 1903.718347554939,
"count": 232548,
"self": 1508.9598804556786,
"children": {
"SubprocessEnvManager._take_step": {
"total": 392.1822489561846,
"count": 232548,
"self": 15.023913221142266,
"children": {
"TorchPolicy.evaluate": {
"total": 377.15833573504233,
"count": 222914,
"self": 377.15833573504233
}
}
},
"workers": {
"total": 2.5762181430759483,
"count": 232548,
"self": 0.0,
"children": {
"worker_root": {
"total": 2389.385928975143,
"count": 232548,
"is_parallel": true,
"self": 1155.7769004990878,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001153229999999894,
"count": 1,
"is_parallel": true,
"self": 0.00032219000058830716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008310399994115869,
"count": 2,
"is_parallel": true,
"self": 0.0008310399994115869
}
}
},
"UnityEnvironment.step": {
"total": 0.02915851699981431,
"count": 1,
"is_parallel": true,
"self": 0.0002854529993783217,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000197045000277285,
"count": 1,
"is_parallel": true,
"self": 0.000197045000277285
},
"communicator.exchange": {
"total": 0.028037420000146085,
"count": 1,
"is_parallel": true,
"self": 0.028037420000146085
},
"steps_from_proto": {
"total": 0.0006385990000126185,
"count": 1,
"is_parallel": true,
"self": 0.00017318100026386674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00046541799974875175,
"count": 2,
"is_parallel": true,
"self": 0.00046541799974875175
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1233.6090284760553,
"count": 232547,
"is_parallel": true,
"self": 37.18883857408355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.56352454480793,
"count": 232547,
"is_parallel": true,
"self": 79.56352454480793
},
"communicator.exchange": {
"total": 1030.7682109420507,
"count": 232547,
"is_parallel": true,
"self": 1030.7682109420507
},
"steps_from_proto": {
"total": 86.08845441511312,
"count": 232547,
"is_parallel": true,
"self": 30.21746566796628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.87098874714684,
"count": 465094,
"is_parallel": true,
"self": 55.87098874714684
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.33388632005926,
"count": 232548,
"self": 6.099997225953757,
"children": {
"process_trajectory": {
"total": 148.47192700310825,
"count": 232548,
"self": 147.29165940810935,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1802675949988952,
"count": 10,
"self": 1.1802675949988952
}
}
},
"_update_policy": {
"total": 326.76196209099726,
"count": 97,
"self": 262.49644452302437,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.26551756797289,
"count": 2910,
"self": 64.26551756797289
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.669993232819252e-07,
"count": 1,
"self": 9.669993232819252e-07
},
"TrainerController._save_models": {
"total": 0.09896866799954296,
"count": 1,
"self": 0.0015424869998241775,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09742618099971878,
"count": 1,
"self": 0.09742618099971878
}
}
}
}
}
}
}