Osborn-bh's picture
First Push
57d5912
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8437048196792603,
"min": 0.8400962948799133,
"max": 2.863363265991211,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8083.5361328125,
"min": 8083.5361328125,
"max": 29355.19921875,
"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": 12.488912582397461,
"min": 0.2597814202308655,
"max": 12.488912582397461,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2435.337890625,
"min": 50.39759826660156,
"max": 2514.49951171875,
"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": 0.06423136791985884,
"min": 0.06349278110371646,
"max": 0.07839987614259407,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25692547167943536,
"min": 0.25397112441486586,
"max": 0.3683073149683575,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2198495748726761,
"min": 0.11613841212865915,
"max": 0.263678574386765,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8793982994907044,
"min": 0.4645536485146366,
"max": 1.286800987872423,
"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": 24.59090909090909,
"min": 3.159090909090909,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1082.0,
"min": 139.0,
"max": 1336.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.59090909090909,
"min": 3.159090909090909,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1082.0,
"min": 139.0,
"max": 1336.0,
"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": "1701489957",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701490450"
},
"total": 492.64168773200004,
"count": 1,
"self": 0.324768535000203,
"children": {
"run_training.setup": {
"total": 0.11024541799997678,
"count": 1,
"self": 0.11024541799997678
},
"TrainerController.start_learning": {
"total": 492.20667377899986,
"count": 1,
"self": 0.706546475017376,
"children": {
"TrainerController._reset_env": {
"total": 3.9930455389999224,
"count": 1,
"self": 3.9930455389999224
},
"TrainerController.advance": {
"total": 487.41833636798265,
"count": 18203,
"self": 0.33725250096995296,
"children": {
"env_step": {
"total": 487.0810838670127,
"count": 18203,
"self": 343.871519626025,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.857132687001,
"count": 18203,
"self": 1.6249081900114106,
"children": {
"TorchPolicy.evaluate": {
"total": 141.2322244969896,
"count": 18203,
"self": 141.2322244969896
}
}
},
"workers": {
"total": 0.35243155398666204,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.2558898940049,
"count": 18203,
"is_parallel": true,
"self": 248.38087200899895,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002685124999970867,
"count": 1,
"is_parallel": true,
"self": 0.000750488999983645,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001934635999987222,
"count": 10,
"is_parallel": true,
"self": 0.001934635999987222
}
}
},
"UnityEnvironment.step": {
"total": 0.046697453999968275,
"count": 1,
"is_parallel": true,
"self": 0.0008055220000642294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004576280000492261,
"count": 1,
"is_parallel": true,
"self": 0.0004576280000492261
},
"communicator.exchange": {
"total": 0.042743158999883235,
"count": 1,
"is_parallel": true,
"self": 0.042743158999883235
},
"steps_from_proto": {
"total": 0.002691144999971584,
"count": 1,
"is_parallel": true,
"self": 0.0004871050000474497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022040399999241345,
"count": 10,
"is_parallel": true,
"self": 0.0022040399999241345
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.87501788500595,
"count": 18202,
"is_parallel": true,
"self": 11.065806506015178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.815046796994693,
"count": 18202,
"is_parallel": true,
"self": 6.815046796994693
},
"communicator.exchange": {
"total": 184.56220045699843,
"count": 18202,
"is_parallel": true,
"self": 184.56220045699843
},
"steps_from_proto": {
"total": 40.43196412499765,
"count": 18202,
"is_parallel": true,
"self": 6.948608682047734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.483355442949915,
"count": 182020,
"is_parallel": true,
"self": 33.483355442949915
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024321399996551918,
"count": 1,
"self": 0.00024321399996551918,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 485.0056994940767,
"count": 267513,
"is_parallel": true,
"self": 7.506051085135368,
"children": {
"process_trajectory": {
"total": 258.48333798194153,
"count": 267513,
"is_parallel": true,
"self": 257.9595871439417,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5237508379998417,
"count": 4,
"is_parallel": true,
"self": 0.5237508379998417
}
}
},
"_update_policy": {
"total": 219.01631042699978,
"count": 90,
"is_parallel": true,
"self": 75.31265451000604,
"children": {
"TorchPPOOptimizer.update": {
"total": 143.70365591699374,
"count": 4584,
"is_parallel": true,
"self": 143.70365591699374
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08850218299994594,
"count": 1,
"self": 0.0010516750000988395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0874505079998471,
"count": 1,
"self": 0.0874505079998471
}
}
}
}
}
}
}