ppo-Huggy / run_logs /timers.json
manojkumarvohra's picture
Huggy
5dc10c3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3984947204589844,
"min": 1.3984947204589844,
"max": 1.426379680633545,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67976.6328125,
"min": 67402.6484375,
"max": 77987.734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 122.10049019607843,
"min": 96.685546875,
"max": 361.71014492753625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49817.0,
"min": 48935.0,
"max": 50181.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999564.0,
"min": 49789.0,
"max": 1999564.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999564.0,
"min": 49789.0,
"max": 1999564.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.1902971267700195,
"min": 0.03379008546471596,
"max": 2.4005179405212402,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 893.6412353515625,
"min": 4.629241943359375,
"max": 1207.4605712890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.1612528035161542,
"min": 1.6893211453065384,
"max": 3.912124333158876,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1289.791143834591,
"min": 231.43699690699577,
"max": 1967.7985395789146,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.1612528035161542,
"min": 1.6893211453065384,
"max": 3.912124333158876,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1289.791143834591,
"min": 231.43699690699577,
"max": 1967.7985395789146,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01702043063851306,
"min": 0.014018045664286346,
"max": 0.02064868421617171,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03404086127702612,
"min": 0.02827296258401475,
"max": 0.061946052648515125,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04574800475190083,
"min": 0.023595172125432228,
"max": 0.07158500204483667,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09149600950380166,
"min": 0.04813631164530913,
"max": 0.21276669477423032,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.1178236274250115e-06,
"min": 4.1178236274250115e-06,
"max": 0.00029533297655567496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.235647254850023e-06,
"min": 8.235647254850023e-06,
"max": 0.0008438665687111498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137257500000002,
"min": 0.10137257500000002,
"max": 0.198444325,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20274515000000004,
"min": 0.20274515000000004,
"max": 0.5812888500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.849149250000019e-05,
"min": 7.849149250000019e-05,
"max": 0.004922371817500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015698298500000038,
"min": 0.00015698298500000038,
"max": 0.014066313615000003,
"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": "1726830368",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726832803"
},
"total": 2435.331208922,
"count": 1,
"self": 0.43528264499991565,
"children": {
"run_training.setup": {
"total": 0.05538453899998785,
"count": 1,
"self": 0.05538453899998785
},
"TrainerController.start_learning": {
"total": 2434.840541738,
"count": 1,
"self": 4.307514678039752,
"children": {
"TrainerController._reset_env": {
"total": 2.899869049000017,
"count": 1,
"self": 2.899869049000017
},
"TrainerController.advance": {
"total": 2427.51580410996,
"count": 231035,
"self": 4.5095802489427115,
"children": {
"env_step": {
"total": 1923.9200206410296,
"count": 231035,
"self": 1515.158303620117,
"children": {
"SubprocessEnvManager._take_step": {
"total": 406.0409137398874,
"count": 231035,
"self": 15.766320755833362,
"children": {
"TorchPolicy.evaluate": {
"total": 390.27459298405404,
"count": 222908,
"self": 390.27459298405404
}
}
},
"workers": {
"total": 2.7208032810251552,
"count": 231035,
"self": 0.0,
"children": {
"worker_root": {
"total": 2427.7338142020158,
"count": 231035,
"is_parallel": true,
"self": 1201.3518510039196,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008397049999757655,
"count": 1,
"is_parallel": true,
"self": 0.00021827899990967126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006214260000660943,
"count": 2,
"is_parallel": true,
"self": 0.0006214260000660943
}
}
},
"UnityEnvironment.step": {
"total": 0.04176065199999357,
"count": 1,
"is_parallel": true,
"self": 0.000383181999950466,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002120240000067497,
"count": 1,
"is_parallel": true,
"self": 0.0002120240000067497
},
"communicator.exchange": {
"total": 0.040399406999995335,
"count": 1,
"is_parallel": true,
"self": 0.040399406999995335
},
"steps_from_proto": {
"total": 0.0007660390000410189,
"count": 1,
"is_parallel": true,
"self": 0.00021541600006003137,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005506229999809875,
"count": 2,
"is_parallel": true,
"self": 0.0005506229999809875
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1226.3819631980962,
"count": 231034,
"is_parallel": true,
"self": 37.50324346812181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.55281054996999,
"count": 231034,
"is_parallel": true,
"self": 80.55281054996999
},
"communicator.exchange": {
"total": 1020.6579342729985,
"count": 231034,
"is_parallel": true,
"self": 1020.6579342729985
},
"steps_from_proto": {
"total": 87.66797490700571,
"count": 231034,
"is_parallel": true,
"self": 31.11179722384111,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.556177683164606,
"count": 462068,
"is_parallel": true,
"self": 56.556177683164606
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.0862032199876,
"count": 231035,
"self": 6.864263311084528,
"children": {
"process_trajectory": {
"total": 153.03155124190175,
"count": 231035,
"self": 151.72920359590148,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3023476460002712,
"count": 10,
"self": 1.3023476460002712
}
}
},
"_update_policy": {
"total": 339.19038866700134,
"count": 96,
"self": 272.91527208299567,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.27511658400567,
"count": 2880,
"self": 66.27511658400567
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1080001058871858e-06,
"count": 1,
"self": 1.1080001058871858e-06
},
"TrainerController._save_models": {
"total": 0.11735279300000911,
"count": 1,
"self": 0.001968946000033611,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1153838469999755,
"count": 1,
"self": 0.1153838469999755
}
}
}
}
}
}
}