ppo-Huggy / run_logs /timers.json
niv6395's picture
Huggy
70a31fd verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408152461051941,
"min": 1.408152461051941,
"max": 1.431304693222046,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69941.5234375,
"min": 68777.9921875,
"max": 77270.0625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.18035714285715,
"min": 88.18035714285715,
"max": 384.4153846153846,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49381.0,
"min": 49072.0,
"max": 50012.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999932.0,
"min": 49931.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999932.0,
"min": 49931.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3311784267425537,
"min": -0.02695563994348049,
"max": 2.407205581665039,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1305.4599609375,
"min": -3.4772775173187256,
"max": 1305.4599609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6569852462836674,
"min": 1.789939160725867,
"max": 3.9051120958854035,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2047.9117379188538,
"min": 230.90215173363686,
"max": 2054.0889624357224,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6569852462836674,
"min": 1.789939160725867,
"max": 3.9051120958854035,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2047.9117379188538,
"min": 230.90215173363686,
"max": 2054.0889624357224,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017130255365110415,
"min": 0.013213489813157744,
"max": 0.020432933419942855,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05139076609533125,
"min": 0.02642697962631549,
"max": 0.059932138317769085,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05398553125560283,
"min": 0.02332703812668721,
"max": 0.065464979948269,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1619565937668085,
"min": 0.04665407625337442,
"max": 0.196394939844807,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2276989241333305e-06,
"min": 3.2276989241333305e-06,
"max": 0.00029533590155470007,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.683096772399991e-06,
"min": 9.683096772399991e-06,
"max": 0.0008438214187261999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107586666666668,
"min": 0.10107586666666668,
"max": 0.19844530000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30322760000000004,
"min": 0.20728000000000008,
"max": 0.5812738,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.368574666666662e-05,
"min": 6.368574666666662e-05,
"max": 0.004922420469999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019105723999999986,
"min": 0.00019105723999999986,
"max": 0.014065562620000003,
"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": "1716943560",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716945914"
},
"total": 2353.9103081000003,
"count": 1,
"self": 0.4384102180001719,
"children": {
"run_training.setup": {
"total": 0.055983930000024884,
"count": 1,
"self": 0.055983930000024884
},
"TrainerController.start_learning": {
"total": 2353.415913952,
"count": 1,
"self": 4.316778764121864,
"children": {
"TrainerController._reset_env": {
"total": 3.6947503679999727,
"count": 1,
"self": 3.6947503679999727
},
"TrainerController.advance": {
"total": 2345.2841261618782,
"count": 231437,
"self": 4.7280404569442,
"children": {
"env_step": {
"total": 1859.801642321931,
"count": 231437,
"self": 1533.3222618498498,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.6963557360659,
"count": 231437,
"self": 16.340135517167823,
"children": {
"TorchPolicy.evaluate": {
"total": 307.3562202188981,
"count": 222898,
"self": 307.3562202188981
}
}
},
"workers": {
"total": 2.783024736015136,
"count": 231437,
"self": 0.0,
"children": {
"worker_root": {
"total": 2346.4399750580783,
"count": 231437,
"is_parallel": true,
"self": 1111.4951549390057,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010471470000084082,
"count": 1,
"is_parallel": true,
"self": 0.00031107400002383656,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007360729999845717,
"count": 2,
"is_parallel": true,
"self": 0.0007360729999845717
}
}
},
"UnityEnvironment.step": {
"total": 0.029375242000014623,
"count": 1,
"is_parallel": true,
"self": 0.0003803439999501279,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001982990000897189,
"count": 1,
"is_parallel": true,
"self": 0.0001982990000897189
},
"communicator.exchange": {
"total": 0.027995426999950723,
"count": 1,
"is_parallel": true,
"self": 0.027995426999950723
},
"steps_from_proto": {
"total": 0.000801172000024053,
"count": 1,
"is_parallel": true,
"self": 0.00020676799999819195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000594404000025861,
"count": 2,
"is_parallel": true,
"self": 0.000594404000025861
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1234.9448201190726,
"count": 231436,
"is_parallel": true,
"self": 37.84079924103753,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.1623528529559,
"count": 231436,
"is_parallel": true,
"self": 79.1623528529559
},
"communicator.exchange": {
"total": 1030.4821018509374,
"count": 231436,
"is_parallel": true,
"self": 1030.4821018509374
},
"steps_from_proto": {
"total": 87.45956617414186,
"count": 231436,
"is_parallel": true,
"self": 31.315529795330576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.14403637881128,
"count": 462872,
"is_parallel": true,
"self": 56.14403637881128
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 480.75444338300304,
"count": 231437,
"self": 6.348192837931379,
"children": {
"process_trajectory": {
"total": 148.45009228407287,
"count": 231437,
"self": 147.14588878507232,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3042034990005504,
"count": 10,
"self": 1.3042034990005504
}
}
},
"_update_policy": {
"total": 325.9561582609988,
"count": 97,
"self": 262.55974446999085,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.396413791007944,
"count": 2910,
"self": 63.396413791007944
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0250000741507392e-06,
"count": 1,
"self": 1.0250000741507392e-06
},
"TrainerController._save_models": {
"total": 0.12025763300016479,
"count": 1,
"self": 0.0019044470000153524,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11835318600014944,
"count": 1,
"self": 0.11835318600014944
}
}
}
}
}
}
}