ppo-Huggy / run_logs /timers.json
alexandre-co's picture
Huggy
f302bab
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4055980443954468,
"min": 1.4055980443954468,
"max": 1.4293746948242188,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71551.96875,
"min": 67382.34375,
"max": 79425.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.81108829568788,
"min": 92.96998123827392,
"max": 428.7692307692308,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49095.0,
"min": 48863.0,
"max": 50184.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999924.0,
"min": 49949.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999924.0,
"min": 49949.0,
"max": 1999924.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4525063037872314,
"min": 0.030634824186563492,
"max": 2.4525063037872314,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1194.37060546875,
"min": 3.5536396503448486,
"max": 1264.831298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.801163296924724,
"min": 1.7495840417927708,
"max": 3.9592853613141785,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1851.1665256023407,
"min": 202.95174884796143,
"max": 2106.339812219143,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.801163296924724,
"min": 1.7495840417927708,
"max": 3.9592853613141785,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1851.1665256023407,
"min": 202.95174884796143,
"max": 2106.339812219143,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015312808406694483,
"min": 0.012028875039929214,
"max": 0.018985243941278894,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030625616813388965,
"min": 0.024057750079858428,
"max": 0.05695573182383668,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050225682494541006,
"min": 0.020885590991626183,
"max": 0.0603673887749513,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10045136498908201,
"min": 0.041771181983252366,
"max": 0.16551494499047598,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.467848510750008e-06,
"min": 4.467848510750008e-06,
"max": 0.0002953662765445749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.935697021500015e-06,
"min": 8.935697021500015e-06,
"max": 0.0008442618185793999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10148925,
"min": 0.10148925,
"max": 0.19845542500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2029785,
"min": 0.2029785,
"max": 0.5814206000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.431357500000017e-05,
"min": 8.431357500000017e-05,
"max": 0.004922925707499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016862715000000035,
"min": 0.00016862715000000035,
"max": 0.01407288794,
"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": "1692805828",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692809073"
},
"total": 3245.5205251509997,
"count": 1,
"self": 0.8452135139996244,
"children": {
"run_training.setup": {
"total": 0.07320628499996928,
"count": 1,
"self": 0.07320628499996928
},
"TrainerController.start_learning": {
"total": 3244.602105352,
"count": 1,
"self": 7.193635223076853,
"children": {
"TrainerController._reset_env": {
"total": 5.240773277000017,
"count": 1,
"self": 5.240773277000017
},
"TrainerController.advance": {
"total": 3231.978014701923,
"count": 231534,
"self": 6.998063783972611,
"children": {
"env_step": {
"total": 2611.1267855749006,
"count": 231534,
"self": 2194.0589325708133,
"children": {
"SubprocessEnvManager._take_step": {
"total": 412.4066425121264,
"count": 231534,
"self": 25.076255957274952,
"children": {
"TorchPolicy.evaluate": {
"total": 387.33038655485143,
"count": 222976,
"self": 387.33038655485143
}
}
},
"workers": {
"total": 4.661210491960901,
"count": 231534,
"self": 0.0,
"children": {
"worker_root": {
"total": 3233.1571067139794,
"count": 231534,
"is_parallel": true,
"self": 1457.2055676698787,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001188651999996182,
"count": 1,
"is_parallel": true,
"self": 0.0003435490000356367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008451029999605453,
"count": 2,
"is_parallel": true,
"self": 0.0008451029999605453
}
}
},
"UnityEnvironment.step": {
"total": 0.04370783100000608,
"count": 1,
"is_parallel": true,
"self": 0.00034668700004658604,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023577399997520843,
"count": 1,
"is_parallel": true,
"self": 0.00023577399997520843
},
"communicator.exchange": {
"total": 0.04225899599998684,
"count": 1,
"is_parallel": true,
"self": 0.04225899599998684
},
"steps_from_proto": {
"total": 0.0008663739999974496,
"count": 1,
"is_parallel": true,
"self": 0.00025424999989809294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006121240000993566,
"count": 2,
"is_parallel": true,
"self": 0.0006121240000993566
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1775.9515390441006,
"count": 231533,
"is_parallel": true,
"self": 52.07187659688111,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 101.60661343201991,
"count": 231533,
"is_parallel": true,
"self": 101.60661343201991
},
"communicator.exchange": {
"total": 1493.4597851891726,
"count": 231533,
"is_parallel": true,
"self": 1493.4597851891726
},
"steps_from_proto": {
"total": 128.81326382602697,
"count": 231533,
"is_parallel": true,
"self": 44.988369562985895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.82489426304107,
"count": 463066,
"is_parallel": true,
"self": 83.82489426304107
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 613.8531653430493,
"count": 231534,
"self": 10.774350545106131,
"children": {
"process_trajectory": {
"total": 170.1537132549414,
"count": 231534,
"self": 168.69420515894217,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4595080959992401,
"count": 10,
"self": 1.4595080959992401
}
}
},
"_update_policy": {
"total": 432.9251015430018,
"count": 96,
"self": 367.7314018340127,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.19369970898913,
"count": 2880,
"self": 65.19369970898913
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4750003174412996e-06,
"count": 1,
"self": 1.4750003174412996e-06
},
"TrainerController._save_models": {
"total": 0.18968067500009056,
"count": 1,
"self": 0.002816113000335463,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1868645619997551,
"count": 1,
"self": 0.1868645619997551
}
}
}
}
}
}
}