ppo-Huggy / run_logs /timers.json
ravkumar's picture
Huggy
304e31a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4023445844650269,
"min": 1.4023445844650269,
"max": 1.4281913042068481,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69975.59375,
"min": 69270.546875,
"max": 76131.0546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.00590841949779,
"min": 71.20231213872832,
"max": 381.39694656488547,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48748.0,
"min": 48748.0,
"max": 50158.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999862.0,
"min": 49816.0,
"max": 1999862.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999862.0,
"min": 49816.0,
"max": 1999862.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5135881900787354,
"min": 0.22689597308635712,
"max": 2.5433967113494873,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1701.69921875,
"min": 29.496477127075195,
"max": 1716.1962890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9878996295450007,
"min": 1.9192723530989426,
"max": 4.032141271248049,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2699.8080492019653,
"min": 249.50540590286255,
"max": 2699.8080492019653,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9878996295450007,
"min": 1.9192723530989426,
"max": 4.032141271248049,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2699.8080492019653,
"min": 249.50540590286255,
"max": 2699.8080492019653,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01683890226478171,
"min": 0.012702407438094573,
"max": 0.01992093411293657,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050516706794345126,
"min": 0.02577687323015804,
"max": 0.056739606119420694,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06183934667044216,
"min": 0.021533804262677828,
"max": 0.06617754784723123,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18551804001132646,
"min": 0.043067608525355655,
"max": 0.18633579735954603,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.947098684333345e-06,
"min": 3.947098684333345e-06,
"max": 0.00029533822655392495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1841296053000036e-05,
"min": 1.1841296053000036e-05,
"max": 0.0008442441185853,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131566666666664,
"min": 0.10131566666666664,
"max": 0.19844607500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039469999999999,
"min": 0.20776290000000003,
"max": 0.5814147000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.565176666666686e-05,
"min": 7.565176666666686e-05,
"max": 0.0049224591425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002269553000000006,
"min": 0.0002269553000000006,
"max": 0.01407259353,
"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": "1682884374",
"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": "1682886716"
},
"total": 2342.4293663060002,
"count": 1,
"self": 0.44644845699986035,
"children": {
"run_training.setup": {
"total": 0.09435488600001918,
"count": 1,
"self": 0.09435488600001918
},
"TrainerController.start_learning": {
"total": 2341.8885629630004,
"count": 1,
"self": 4.161864692952349,
"children": {
"TrainerController._reset_env": {
"total": 4.451266626999995,
"count": 1,
"self": 4.451266626999995
},
"TrainerController.advance": {
"total": 2333.152037652048,
"count": 233393,
"self": 4.341799534063284,
"children": {
"env_step": {
"total": 1808.7463663849487,
"count": 233393,
"self": 1524.711146760911,
"children": {
"SubprocessEnvManager._take_step": {
"total": 281.30642319096023,
"count": 233393,
"self": 16.534622889914544,
"children": {
"TorchPolicy.evaluate": {
"total": 264.7718003010457,
"count": 222921,
"self": 264.7718003010457
}
}
},
"workers": {
"total": 2.728796433077264,
"count": 233393,
"self": 0.0,
"children": {
"worker_root": {
"total": 2334.33624576896,
"count": 233393,
"is_parallel": true,
"self": 1088.4577471779517,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010340560000940968,
"count": 1,
"is_parallel": true,
"self": 0.0003445940001256531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006894619999684437,
"count": 2,
"is_parallel": true,
"self": 0.0006894619999684437
}
}
},
"UnityEnvironment.step": {
"total": 0.0274092390000078,
"count": 1,
"is_parallel": true,
"self": 0.0003227309999829231,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001692280000042956,
"count": 1,
"is_parallel": true,
"self": 0.0001692280000042956
},
"communicator.exchange": {
"total": 0.02627974400002131,
"count": 1,
"is_parallel": true,
"self": 0.02627974400002131
},
"steps_from_proto": {
"total": 0.0006375359999992725,
"count": 1,
"is_parallel": true,
"self": 0.00019832899999983056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004392069999994419,
"count": 2,
"is_parallel": true,
"self": 0.0004392069999994419
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.8784985910083,
"count": 233392,
"is_parallel": true,
"self": 36.270475445888906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.02411205706755,
"count": 233392,
"is_parallel": true,
"self": 76.02411205706755
},
"communicator.exchange": {
"total": 1044.6224436780585,
"count": 233392,
"is_parallel": true,
"self": 1044.6224436780585
},
"steps_from_proto": {
"total": 88.96146740999325,
"count": 233392,
"is_parallel": true,
"self": 33.24347902684394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.717988383149304,
"count": 466784,
"is_parallel": true,
"self": 55.717988383149304
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 520.0638717330361,
"count": 233393,
"self": 6.248495716970183,
"children": {
"process_trajectory": {
"total": 135.37359839606643,
"count": 233393,
"self": 134.1037193190665,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2698790769999277,
"count": 10,
"self": 1.2698790769999277
}
}
},
"_update_policy": {
"total": 378.44177761999947,
"count": 97,
"self": 319.3303335339866,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.11144408601285,
"count": 2910,
"self": 59.11144408601285
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.03899992609513e-06,
"count": 1,
"self": 1.03899992609513e-06
},
"TrainerController._save_models": {
"total": 0.12339295200035849,
"count": 1,
"self": 0.002324097999917285,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1210688540004412,
"count": 1,
"self": 0.1210688540004412
}
}
}
}
}
}
}