infatum's picture
First Push
4727e00
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8728518486022949,
"min": 0.8728518486022949,
"max": 2.865591287612915,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8353.1923828125,
"min": 8353.1923828125,
"max": 29378.04296875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.525195121765137,
"min": 0.2462272197008133,
"max": 12.525195121765137,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2442.4130859375,
"min": 47.76808166503906,
"max": 2524.722412109375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07493399640011107,
"min": 0.06284377402684471,
"max": 0.07493399640011107,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2997359856004443,
"min": 0.25137509610737885,
"max": 0.359339018304394,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19091488574357593,
"min": 0.11325358638115336,
"max": 0.2883799722272099,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7636595429743037,
"min": 0.45301434552461345,
"max": 1.4418998611360494,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.727272727272727,
"min": 3.090909090909091,
"max": 24.87272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1088.0,
"min": 136.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.727272727272727,
"min": 3.090909090909091,
"max": 24.87272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1088.0,
"min": 136.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681224104",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1681224576"
},
"total": 472.69022683800006,
"count": 1,
"self": 0.4344730170001867,
"children": {
"run_training.setup": {
"total": 0.1969398399999136,
"count": 1,
"self": 0.1969398399999136
},
"TrainerController.start_learning": {
"total": 472.05881398099996,
"count": 1,
"self": 0.5790478220019395,
"children": {
"TrainerController._reset_env": {
"total": 4.144626438000046,
"count": 1,
"self": 4.144626438000046
},
"TrainerController.advance": {
"total": 467.19384536699795,
"count": 18204,
"self": 0.28529436800295116,
"children": {
"env_step": {
"total": 466.908550998995,
"count": 18204,
"self": 339.18445907900764,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.43642369099416,
"count": 18204,
"self": 1.857842656985099,
"children": {
"TorchPolicy.evaluate": {
"total": 125.57858103400906,
"count": 18204,
"self": 125.57858103400906
}
}
},
"workers": {
"total": 0.28766822899319777,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 470.6372433960089,
"count": 18204,
"is_parallel": true,
"self": 217.11498686400932,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005907167000032132,
"count": 1,
"is_parallel": true,
"self": 0.0035203809997028657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023867860003292662,
"count": 10,
"is_parallel": true,
"self": 0.0023867860003292662
}
}
},
"UnityEnvironment.step": {
"total": 0.03929439499995624,
"count": 1,
"is_parallel": true,
"self": 0.0004235429997834217,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042996400009087665,
"count": 1,
"is_parallel": true,
"self": 0.00042996400009087665
},
"communicator.exchange": {
"total": 0.03666650600007415,
"count": 1,
"is_parallel": true,
"self": 0.03666650600007415
},
"steps_from_proto": {
"total": 0.0017743820000077903,
"count": 1,
"is_parallel": true,
"self": 0.00040642499959631095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013679570004114794,
"count": 10,
"is_parallel": true,
"self": 0.0013679570004114794
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.52225653199957,
"count": 18203,
"is_parallel": true,
"self": 10.145724072002736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.699739303998513,
"count": 18203,
"is_parallel": true,
"self": 5.699739303998513
},
"communicator.exchange": {
"total": 203.34094694300074,
"count": 18203,
"is_parallel": true,
"self": 203.34094694300074
},
"steps_from_proto": {
"total": 34.33584621299758,
"count": 18203,
"is_parallel": true,
"self": 6.802994595982682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.5328516170149,
"count": 182030,
"is_parallel": true,
"self": 27.5328516170149
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001149619999978313,
"count": 1,
"self": 0.0001149619999978313,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 463.5517922749817,
"count": 435018,
"is_parallel": true,
"self": 10.392688076954187,
"children": {
"process_trajectory": {
"total": 256.3006637630276,
"count": 435018,
"is_parallel": true,
"self": 255.17607759802763,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1245861649999824,
"count": 4,
"is_parallel": true,
"self": 1.1245861649999824
}
}
},
"_update_policy": {
"total": 196.85844043499992,
"count": 90,
"is_parallel": true,
"self": 73.72130479599969,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.13713563900023,
"count": 4584,
"is_parallel": true,
"self": 123.13713563900023
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14117939200002638,
"count": 1,
"self": 0.0009409049999931085,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14023848700003327,
"count": 1,
"self": 0.14023848700003327
}
}
}
}
}
}
}