ppo-Huggy / run_logs /timers.json
GarciaDos's picture
Huggy
5285dd0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4056557416915894,
"min": 1.4056557416915894,
"max": 1.428066372871399,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69987.6015625,
"min": 68271.2109375,
"max": 77601.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.41106719367589,
"min": 78.92332268370608,
"max": 413.25619834710744,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49290.0,
"min": 49184.0,
"max": 50075.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49664.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49664.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.380152940750122,
"min": -0.025212755426764488,
"max": 2.5182478427886963,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1204.357421875,
"min": -3.0255305767059326,
"max": 1528.305908203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.534410876012131,
"min": 1.7100907685856024,
"max": 4.014890279840021,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1788.4119032621384,
"min": 205.2108922302723,
"max": 2468.2928746938705,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.534410876012131,
"min": 1.7100907685856024,
"max": 4.014890279840021,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1788.4119032621384,
"min": 205.2108922302723,
"max": 2468.2928746938705,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018493772126061635,
"min": 0.013313318643001063,
"max": 0.021257811509228,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0554813163781849,
"min": 0.026626637286002126,
"max": 0.0554813163781849,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050782068156533765,
"min": 0.021518528244147697,
"max": 0.06030631878723701,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1523462044696013,
"min": 0.043037056488295394,
"max": 0.16828849849601588,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.360898879733342e-06,
"min": 3.360898879733342e-06,
"max": 0.00029531032656322505,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0082696639200025e-05,
"min": 1.0082696639200025e-05,
"max": 0.0008437176187608001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112026666666668,
"min": 0.10112026666666668,
"max": 0.19843677500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30336080000000004,
"min": 0.20736924999999995,
"max": 0.5812392000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.590130666666682e-05,
"min": 6.590130666666682e-05,
"max": 0.004921995072500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019770392000000047,
"min": 0.00019770392000000047,
"max": 0.01406383608,
"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": "1718017389",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1718020017"
},
"total": 2628.285120875,
"count": 1,
"self": 0.39087462299994513,
"children": {
"run_training.setup": {
"total": 0.05690825899989704,
"count": 1,
"self": 0.05690825899989704
},
"TrainerController.start_learning": {
"total": 2627.837337993,
"count": 1,
"self": 4.945261924015085,
"children": {
"TrainerController._reset_env": {
"total": 3.3554184739999755,
"count": 1,
"self": 3.3554184739999755
},
"TrainerController.advance": {
"total": 2619.4219384669846,
"count": 232349,
"self": 4.983895541973197,
"children": {
"env_step": {
"total": 2070.5187515609996,
"count": 232349,
"self": 1708.4579460138393,
"children": {
"SubprocessEnvManager._take_step": {
"total": 358.81203832712856,
"count": 232349,
"self": 18.041882414100883,
"children": {
"TorchPolicy.evaluate": {
"total": 340.7701559130277,
"count": 223032,
"self": 340.7701559130277
}
}
},
"workers": {
"total": 3.2487672200315956,
"count": 232349,
"self": 0.0,
"children": {
"worker_root": {
"total": 2620.256445200037,
"count": 232349,
"is_parallel": true,
"self": 1243.567024462027,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009523339999759628,
"count": 1,
"is_parallel": true,
"self": 0.0002634650001027694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006888689998731934,
"count": 2,
"is_parallel": true,
"self": 0.0006888689998731934
}
}
},
"UnityEnvironment.step": {
"total": 0.0533797540000478,
"count": 1,
"is_parallel": true,
"self": 0.00041657300005226716,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021587599997019424,
"count": 1,
"is_parallel": true,
"self": 0.00021587599997019424
},
"communicator.exchange": {
"total": 0.051947978000043804,
"count": 1,
"is_parallel": true,
"self": 0.051947978000043804
},
"steps_from_proto": {
"total": 0.0007993269999815311,
"count": 1,
"is_parallel": true,
"self": 0.0002499649999663234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005493620000152077,
"count": 2,
"is_parallel": true,
"self": 0.0005493620000152077
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1376.68942073801,
"count": 232348,
"is_parallel": true,
"self": 40.129231899123624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.09602503791825,
"count": 232348,
"is_parallel": true,
"self": 88.09602503791825
},
"communicator.exchange": {
"total": 1151.5390811030195,
"count": 232348,
"is_parallel": true,
"self": 1151.5390811030195
},
"steps_from_proto": {
"total": 96.92508269794871,
"count": 232348,
"is_parallel": true,
"self": 36.86167779692744,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.06340490102127,
"count": 464696,
"is_parallel": true,
"self": 60.06340490102127
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 543.9192913640118,
"count": 232349,
"self": 7.2626353889786515,
"children": {
"process_trajectory": {
"total": 171.0512412230338,
"count": 232349,
"self": 169.32648556403353,
"children": {
"RLTrainer._checkpoint": {
"total": 1.724755659000266,
"count": 10,
"self": 1.724755659000266
}
}
},
"_update_policy": {
"total": 365.6054147519993,
"count": 97,
"self": 298.04661867500545,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.55879607699387,
"count": 2910,
"self": 67.55879607699387
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0040002962341532e-06,
"count": 1,
"self": 1.0040002962341532e-06
},
"TrainerController._save_models": {
"total": 0.11471812399986447,
"count": 1,
"self": 0.002382824999585864,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11233529900027861,
"count": 1,
"self": 0.11233529900027861
}
}
}
}
}
}
}