ppo-Huggy-1 / run_logs /timers.json
ravkumar's picture
Huggy
58b0965
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030345678329468,
"min": 1.4030205011367798,
"max": 1.4270918369293213,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69531.5859375,
"min": 68915.28125,
"max": 76777.265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.56213017751479,
"min": 87.6495575221239,
"max": 399.552,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49464.0,
"min": 48905.0,
"max": 50065.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999966.0,
"min": 49964.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999966.0,
"min": 49964.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4506402015686035,
"min": 0.15911823511123657,
"max": 2.4537792205810547,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1242.474609375,
"min": 19.730661392211914,
"max": 1328.14990234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8183123541066397,
"min": 1.8847150160901007,
"max": 3.9584148702095017,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1935.8843635320663,
"min": 233.7046619951725,
"max": 2084.1145710349083,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8183123541066397,
"min": 1.8847150160901007,
"max": 3.9584148702095017,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1935.8843635320663,
"min": 233.7046619951725,
"max": 2084.1145710349083,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01760141650835673,
"min": 0.013692461181360867,
"max": 0.020845646575132076,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052804249525070186,
"min": 0.028151864864048547,
"max": 0.06253693972539623,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05230199115143882,
"min": 0.02254065542171399,
"max": 0.060361966904666685,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15690597345431645,
"min": 0.04508131084342798,
"max": 0.18108590071400005,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6442987852666753e-06,
"min": 3.6442987852666753e-06,
"max": 0.0002953601265466249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0932896355800026e-05,
"min": 1.0932896355800026e-05,
"max": 0.00084429766856745,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121473333333335,
"min": 0.10121473333333335,
"max": 0.19845337500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364420000000003,
"min": 0.20761880000000002,
"max": 0.5814325500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.061519333333349e-05,
"min": 7.061519333333349e-05,
"max": 0.004922823412499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021184558000000048,
"min": 0.00021184558000000048,
"max": 0.014073484245,
"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": "1683403254",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "1683405578"
},
"total": 2324.039756779,
"count": 1,
"self": 0.74322380600006,
"children": {
"run_training.setup": {
"total": 0.040559055000017,
"count": 1,
"self": 0.040559055000017
},
"TrainerController.start_learning": {
"total": 2323.255973918,
"count": 1,
"self": 4.102785957066317,
"children": {
"TrainerController._reset_env": {
"total": 5.428476485000033,
"count": 1,
"self": 5.428476485000033
},
"TrainerController.advance": {
"total": 2313.5308422489343,
"count": 231958,
"self": 4.448409063973486,
"children": {
"env_step": {
"total": 1799.5364757100192,
"count": 231958,
"self": 1520.0893821609866,
"children": {
"SubprocessEnvManager._take_step": {
"total": 276.8138920500842,
"count": 231958,
"self": 16.247210641051424,
"children": {
"TorchPolicy.evaluate": {
"total": 260.56668140903275,
"count": 222908,
"self": 260.56668140903275
}
}
},
"workers": {
"total": 2.6332014989485515,
"count": 231958,
"self": 0.0,
"children": {
"worker_root": {
"total": 2315.5315811940827,
"count": 231958,
"is_parallel": true,
"self": 1070.789784988965,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007855320000089705,
"count": 1,
"is_parallel": true,
"self": 0.00023933400007081218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005461979999381583,
"count": 2,
"is_parallel": true,
"self": 0.0005461979999381583
}
}
},
"UnityEnvironment.step": {
"total": 0.02876165299994682,
"count": 1,
"is_parallel": true,
"self": 0.0003085439998358197,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015390999999453925,
"count": 1,
"is_parallel": true,
"self": 0.00015390999999453925
},
"communicator.exchange": {
"total": 0.027598954000040976,
"count": 1,
"is_parallel": true,
"self": 0.027598954000040976
},
"steps_from_proto": {
"total": 0.0007002450000754834,
"count": 1,
"is_parallel": true,
"self": 0.00018702100010159484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005132239999738886,
"count": 2,
"is_parallel": true,
"self": 0.0005132239999738886
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1244.7417962051177,
"count": 231957,
"is_parallel": true,
"self": 38.103702791071555,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.82747616295887,
"count": 231957,
"is_parallel": true,
"self": 76.82747616295887
},
"communicator.exchange": {
"total": 1038.5030497220291,
"count": 231957,
"is_parallel": true,
"self": 1038.5030497220291
},
"steps_from_proto": {
"total": 91.30756752905802,
"count": 231957,
"is_parallel": true,
"self": 33.04471660615013,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.26285092290789,
"count": 463914,
"is_parallel": true,
"self": 58.26285092290789
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 509.5459574749417,
"count": 231958,
"self": 6.041992000969117,
"children": {
"process_trajectory": {
"total": 127.93807353797217,
"count": 231958,
"self": 126.47966331597195,
"children": {
"RLTrainer._checkpoint": {
"total": 1.458410222000225,
"count": 10,
"self": 1.458410222000225
}
}
},
"_update_policy": {
"total": 375.5658919360004,
"count": 97,
"self": 316.6038829010149,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.9620090349855,
"count": 2910,
"self": 58.9620090349855
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2149998838140164e-06,
"count": 1,
"self": 1.2149998838140164e-06
},
"TrainerController._save_models": {
"total": 0.1938680119997116,
"count": 1,
"self": 0.0028052029997525096,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1910628089999591,
"count": 1,
"self": 0.1910628089999591
}
}
}
}
}
}
}