demelin's picture
Huggy
9864d5f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 0.925949215888977,
"min": 0.925949215888977,
"max": 1.4118565320968628,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 47167.8515625,
"min": 46029.765625,
"max": 75925.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.5314401622718,
"min": 96.61689587426326,
"max": 418.0416666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49562.0,
"min": 49023.0,
"max": 50165.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49612.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49612.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.314250946044922,
"min": -0.11194455623626709,
"max": 2.3699111938476562,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1140.9256591796875,
"min": -13.321402549743652,
"max": 1216.3016357421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.730839757962836,
"min": 1.5808309649719912,
"max": 4.062930404341647,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1839.3040006756783,
"min": 188.11888483166695,
"max": 1999.07195687294,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.730839757962836,
"min": 1.5808309649719912,
"max": 4.062930404341647,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1839.3040006756783,
"min": 188.11888483166695,
"max": 1999.07195687294,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01726920791487727,
"min": 0.014723236522695516,
"max": 0.022921211044498097,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05180762374463181,
"min": 0.029446473045391032,
"max": 0.06773997600830625,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03271867034749852,
"min": 0.019258403529723484,
"max": 0.26193915683155256,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09815601104249556,
"min": 0.039330695072809854,
"max": 0.5238783136631051,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.455109884829998e-05,
"min": 3.455109884829998e-05,
"max": 0.00295264650157845,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00010365329654489996,
"min": 0.00010365329654489996,
"max": 0.008439330018689,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011517,
"min": 0.1011517,
"max": 0.19842155,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034551,
"min": 0.20746595,
"max": 0.5813110000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.746983e-05,
"min": 6.746983e-05,
"max": 0.004921235345,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020240949,
"min": 0.00020240949,
"max": 0.0140674189,
"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": "1720202996",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720205305"
},
"total": 2308.9715572249997,
"count": 1,
"self": 0.4318869359999553,
"children": {
"run_training.setup": {
"total": 0.05512478299999657,
"count": 1,
"self": 0.05512478299999657
},
"TrainerController.start_learning": {
"total": 2308.484545506,
"count": 1,
"self": 4.09580170508525,
"children": {
"TrainerController._reset_env": {
"total": 3.004210284999999,
"count": 1,
"self": 3.004210284999999
},
"TrainerController.advance": {
"total": 2301.267043933915,
"count": 231184,
"self": 4.683859602987923,
"children": {
"env_step": {
"total": 1832.0061439539627,
"count": 231184,
"self": 1507.5691757290247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 321.7531882979248,
"count": 231184,
"self": 16.082754232860452,
"children": {
"TorchPolicy.evaluate": {
"total": 305.67043406506434,
"count": 222950,
"self": 305.67043406506434
}
}
},
"workers": {
"total": 2.6837799270133473,
"count": 231184,
"self": 0.0,
"children": {
"worker_root": {
"total": 2301.4951946470715,
"count": 231184,
"is_parallel": true,
"self": 1089.6212621490195,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008712289999266432,
"count": 1,
"is_parallel": true,
"self": 0.00020938799991654378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006618410000100994,
"count": 2,
"is_parallel": true,
"self": 0.0006618410000100994
}
}
},
"UnityEnvironment.step": {
"total": 0.030152983999983007,
"count": 1,
"is_parallel": true,
"self": 0.0003644879999455952,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018338100005621527,
"count": 1,
"is_parallel": true,
"self": 0.00018338100005621527
},
"communicator.exchange": {
"total": 0.02886019300001408,
"count": 1,
"is_parallel": true,
"self": 0.02886019300001408
},
"steps_from_proto": {
"total": 0.0007449219999671186,
"count": 1,
"is_parallel": true,
"self": 0.00021031999995102524,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005346020000160934,
"count": 2,
"is_parallel": true,
"self": 0.0005346020000160934
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1211.873932498052,
"count": 231183,
"is_parallel": true,
"self": 37.74601301922894,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.09946873889407,
"count": 231183,
"is_parallel": true,
"self": 79.09946873889407
},
"communicator.exchange": {
"total": 1009.0967210989868,
"count": 231183,
"is_parallel": true,
"self": 1009.0967210989868
},
"steps_from_proto": {
"total": 85.9317296409422,
"count": 231183,
"is_parallel": true,
"self": 30.46351751805969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.468212122882505,
"count": 462366,
"is_parallel": true,
"self": 55.468212122882505
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 464.57704037696453,
"count": 231184,
"self": 6.350202445941363,
"children": {
"process_trajectory": {
"total": 140.60752912902353,
"count": 231184,
"self": 139.18860466002377,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4189244689997622,
"count": 10,
"self": 1.4189244689997622
}
}
},
"_update_policy": {
"total": 317.61930880199964,
"count": 97,
"self": 255.52959628400276,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.08971251799687,
"count": 2910,
"self": 62.08971251799687
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.920001164369751e-07,
"count": 1,
"self": 8.920001164369751e-07
},
"TrainerController._save_models": {
"total": 0.11748868999984552,
"count": 1,
"self": 0.0028528500001812063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11463583999966431,
"count": 1,
"self": 0.11463583999966431
}
}
}
}
}
}
}