ppo-Huggy / run_logs /timers.json
nini36578's picture
Huggy
4f7c5cf verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074894189834595,
"min": 1.4074894189834595,
"max": 1.428376317024231,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70689.75,
"min": 69240.75,
"max": 76119.6328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.75081433224756,
"min": 77.30952380952381,
"max": 416.0083333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49581.0,
"min": 48705.0,
"max": 50250.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999878.0,
"min": 49702.0,
"max": 1999878.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999878.0,
"min": 49702.0,
"max": 1999878.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4428412914276123,
"min": 0.13770955801010132,
"max": 2.4920105934143066,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1499.904541015625,
"min": 16.38743782043457,
"max": 1556.828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.830024583234849,
"min": 1.952939877990915,
"max": 3.993815237775855,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2351.6350941061974,
"min": 232.39984548091888,
"max": 2514.522381365299,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.830024583234849,
"min": 1.952939877990915,
"max": 3.993815237775855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2351.6350941061974,
"min": 232.39984548091888,
"max": 2514.522381365299,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0150545232608743,
"min": 0.014169052870258584,
"max": 0.022063047504828622,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0451635697826229,
"min": 0.02890553458710201,
"max": 0.05678228562852988,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055190869213806254,
"min": 0.021144023972253005,
"max": 0.06664806188394626,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16557260764141876,
"min": 0.04228804794450601,
"max": 0.18120856508612632,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.788248737283336e-06,
"min": 3.788248737283336e-06,
"max": 0.00029533282655572505,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1364746211850008e-05,
"min": 1.1364746211850008e-05,
"max": 0.0008440720686426499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012627166666667,
"min": 0.1012627166666667,
"max": 0.198444275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037881500000001,
"min": 0.20767804999999995,
"max": 0.5813573500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.300956166666669e-05,
"min": 7.300956166666669e-05,
"max": 0.004922369322500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021902868500000005,
"min": 0.00021902868500000005,
"max": 0.014069731765000003,
"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": "1739639233",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739644166"
},
"total": 4932.788845611,
"count": 1,
"self": 0.6941281640001762,
"children": {
"run_training.setup": {
"total": 0.03676400900008048,
"count": 1,
"self": 0.03676400900008048
},
"TrainerController.start_learning": {
"total": 4932.057953438,
"count": 1,
"self": 9.28895372604893,
"children": {
"TrainerController._reset_env": {
"total": 3.9072426850000284,
"count": 1,
"self": 3.9072426850000284
},
"TrainerController.advance": {
"total": 4918.745421175952,
"count": 232977,
"self": 9.004980743983651,
"children": {
"env_step": {
"total": 3196.855658005875,
"count": 232977,
"self": 2663.4406486987427,
"children": {
"SubprocessEnvManager._take_step": {
"total": 527.7582223070681,
"count": 232977,
"self": 34.71353445497493,
"children": {
"TorchPolicy.evaluate": {
"total": 493.04468785209315,
"count": 222954,
"self": 493.04468785209315
}
}
},
"workers": {
"total": 5.656787000064014,
"count": 232977,
"self": 0.0,
"children": {
"worker_root": {
"total": 4917.262199098058,
"count": 232977,
"is_parallel": true,
"self": 2783.3820243518594,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012178950000816258,
"count": 1,
"is_parallel": true,
"self": 0.00045258499994815793,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007653100001334678,
"count": 2,
"is_parallel": true,
"self": 0.0007653100001334678
}
}
},
"UnityEnvironment.step": {
"total": 0.038732464000077016,
"count": 1,
"is_parallel": true,
"self": 0.0004055570000218722,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022733800005880767,
"count": 1,
"is_parallel": true,
"self": 0.00022733800005880767
},
"communicator.exchange": {
"total": 0.037172847999954683,
"count": 1,
"is_parallel": true,
"self": 0.037172847999954683
},
"steps_from_proto": {
"total": 0.0009267210000416526,
"count": 1,
"is_parallel": true,
"self": 0.00025816599986683286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006685550001748197,
"count": 2,
"is_parallel": true,
"self": 0.0006685550001748197
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2133.8801747461985,
"count": 232976,
"is_parallel": true,
"self": 65.99967884821444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 119.70799950006449,
"count": 232976,
"is_parallel": true,
"self": 119.70799950006449
},
"communicator.exchange": {
"total": 1804.8937838901084,
"count": 232976,
"is_parallel": true,
"self": 1804.8937838901084
},
"steps_from_proto": {
"total": 143.27871250781118,
"count": 232976,
"is_parallel": true,
"self": 45.66060116961876,
"children": {
"_process_rank_one_or_two_observation": {
"total": 97.61811133819242,
"count": 465952,
"is_parallel": true,
"self": 97.61811133819242
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1712.8847824260936,
"count": 232977,
"self": 13.997756379979137,
"children": {
"process_trajectory": {
"total": 283.46760673011136,
"count": 232977,
"self": 281.9778732881123,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4897334419990784,
"count": 10,
"self": 1.4897334419990784
}
}
},
"_update_policy": {
"total": 1415.419419316003,
"count": 97,
"self": 359.402135988998,
"children": {
"TorchPPOOptimizer.update": {
"total": 1056.017283327005,
"count": 2910,
"self": 1056.017283327005
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.544999577163253e-06,
"count": 1,
"self": 1.544999577163253e-06
},
"TrainerController._save_models": {
"total": 0.11633430599977146,
"count": 1,
"self": 0.0033308609999949113,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11300344499977655,
"count": 1,
"self": 0.11300344499977655
}
}
}
}
}
}
}