Z. T
First Push
b0b26fc
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.930548369884491,
"min": 0.930548369884491,
"max": 2.8593969345092773,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8905.34765625,
"min": 8905.34765625,
"max": 29377.443359375,
"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": 12.925532341003418,
"min": 0.3973778784275055,
"max": 12.972102165222168,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.478759765625,
"min": 77.09130859375,
"max": 2646.308837890625,
"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": 0.0685314615823947,
"min": 0.061245116572364866,
"max": 0.07396357902770807,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2741258463295788,
"min": 0.25091128311146793,
"max": 0.36981789513854035,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1934840985957314,
"min": 0.12458119080995446,
"max": 0.2757901422533334,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7739363943829256,
"min": 0.49832476323981784,
"max": 1.378950711266667,
"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": 25.818181818181817,
"min": 3.409090909090909,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 150.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.409090909090909,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 150.0,
"max": 1404.0,
"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": "1681836824",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/home/aza/.virtualenvs/mlagents_hf-integration/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": "1681837241"
},
"total": 416.68885721600054,
"count": 1,
"self": 0.4769340380007634,
"children": {
"run_training.setup": {
"total": 0.027272650000668364,
"count": 1,
"self": 0.027272650000668364
},
"TrainerController.start_learning": {
"total": 416.1846505279991,
"count": 1,
"self": 0.6313285467804235,
"children": {
"TrainerController._reset_env": {
"total": 2.4317771469995932,
"count": 1,
"self": 2.4317771469995932
},
"TrainerController.advance": {
"total": 412.9877494612192,
"count": 18210,
"self": 0.27110456310583686,
"children": {
"env_step": {
"total": 412.7166448981134,
"count": 18210,
"self": 333.5456570951483,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.8750086270411,
"count": 18210,
"self": 1.553697858898886,
"children": {
"TorchPolicy.evaluate": {
"total": 77.32131076814221,
"count": 18210,
"self": 77.32131076814221
}
}
},
"workers": {
"total": 0.29597917592400336,
"count": 18210,
"self": 0.0,
"children": {
"worker_root": {
"total": 414.9932808397225,
"count": 18210,
"is_parallel": true,
"self": 164.7312867906876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001240667999809375,
"count": 1,
"is_parallel": true,
"self": 0.00034140800016757566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008992599996417994,
"count": 10,
"is_parallel": true,
"self": 0.0008992599996417994
}
}
},
"UnityEnvironment.step": {
"total": 0.022098477000326966,
"count": 1,
"is_parallel": true,
"self": 0.0002348870002606418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002138859999831766,
"count": 1,
"is_parallel": true,
"self": 0.0002138859999831766
},
"communicator.exchange": {
"total": 0.020900700001220684,
"count": 1,
"is_parallel": true,
"self": 0.020900700001220684
},
"steps_from_proto": {
"total": 0.000749003998862463,
"count": 1,
"is_parallel": true,
"self": 0.00017720899631967768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005717950025427854,
"count": 10,
"is_parallel": true,
"self": 0.0005717950025427854
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.2619940490349,
"count": 18209,
"is_parallel": true,
"self": 6.192755557976852,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.137827668035243,
"count": 18209,
"is_parallel": true,
"self": 4.137827668035243
},
"communicator.exchange": {
"total": 221.55924551108,
"count": 18209,
"is_parallel": true,
"self": 221.55924551108
},
"steps_from_proto": {
"total": 18.37216531194281,
"count": 18209,
"is_parallel": true,
"self": 4.039433125974028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.33273218596878,
"count": 182090,
"is_parallel": true,
"self": 14.33273218596878
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013198099986766465,
"count": 1,
"self": 0.00013198099986766465,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 412.05042877790765,
"count": 177369,
"is_parallel": true,
"self": 3.757652587333723,
"children": {
"process_trajectory": {
"total": 237.2326876875668,
"count": 177369,
"is_parallel": true,
"self": 236.29794356156708,
"children": {
"RLTrainer._checkpoint": {
"total": 0.934744125999714,
"count": 4,
"is_parallel": true,
"self": 0.934744125999714
}
}
},
"_update_policy": {
"total": 171.06008850300714,
"count": 90,
"is_parallel": true,
"self": 30.019638429055703,
"children": {
"TorchPPOOptimizer.update": {
"total": 141.04045007395143,
"count": 4584,
"is_parallel": true,
"self": 141.04045007395143
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13366339200001676,
"count": 1,
"self": 0.02465972499885538,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10900366700116138,
"count": 1,
"self": 0.10900366700116138
}
}
}
}
}
}
}