gabrielbenabou's picture
First Push
5028df6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9192315340042114,
"min": 0.9192315340042114,
"max": 2.8722503185272217,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8797.0458984375,
"min": 8797.0458984375,
"max": 29477.904296875,
"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": 12.675583839416504,
"min": 0.1918199062347412,
"max": 12.675583839416504,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.73876953125,
"min": 37.21306228637695,
"max": 2572.742431640625,
"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.Environment.CumulativeReward.mean": {
"value": 25.09090909090909,
"min": 3.159090909090909,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 139.0,
"max": 1367.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.159090909090909,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 139.0,
"max": 1367.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06375053759763308,
"min": 0.06285092248184738,
"max": 0.07566402355555957,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2550021503905323,
"min": 0.2550021503905323,
"max": 0.37832011777779784,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20342359691858292,
"min": 0.10652379825820818,
"max": 0.2963242155079748,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8136943876743317,
"min": 0.4260951930328327,
"max": 1.481621077539874,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029184900271699997,
"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": 0.19728300000000004,
"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": 0.0048644217,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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": "1708079522",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.21.2",
"end_time_seconds": "1708079916"
},
"total": 393.62493889100006,
"count": 1,
"self": 0.2703265179952723,
"children": {
"run_training.setup": {
"total": 0.01448039500246523,
"count": 1,
"self": 0.01448039500246523
},
"TrainerController.start_learning": {
"total": 393.3401319780023,
"count": 1,
"self": 0.43650310122029623,
"children": {
"TrainerController._reset_env": {
"total": 1.105587543999718,
"count": 1,
"self": 1.105587543999718
},
"TrainerController.advance": {
"total": 391.7385997017773,
"count": 18201,
"self": 0.20346960727329133,
"children": {
"env_step": {
"total": 391.535130094504,
"count": 18201,
"self": 244.68716851486533,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.6104092521491,
"count": 18201,
"self": 1.1776646150974557,
"children": {
"TorchPolicy.evaluate": {
"total": 145.43274463705166,
"count": 18201,
"self": 145.43274463705166
}
}
},
"workers": {
"total": 0.23755232748953858,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 392.62108338120015,
"count": 18201,
"is_parallel": true,
"self": 205.60812447789795,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012301889946684241,
"count": 1,
"is_parallel": true,
"self": 0.000406236998969689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008239519956987351,
"count": 10,
"is_parallel": true,
"self": 0.0008239519956987351
}
}
},
"UnityEnvironment.step": {
"total": 0.023591150995343924,
"count": 1,
"is_parallel": true,
"self": 0.0002002689871005714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005734540027333423,
"count": 1,
"is_parallel": true,
"self": 0.0005734540027333423
},
"communicator.exchange": {
"total": 0.022032102999219205,
"count": 1,
"is_parallel": true,
"self": 0.022032102999219205
},
"steps_from_proto": {
"total": 0.0007853250062908046,
"count": 1,
"is_parallel": true,
"self": 0.00019681201229104772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005885129939997569,
"count": 10,
"is_parallel": true,
"self": 0.0005885129939997569
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 187.0129589033022,
"count": 18200,
"is_parallel": true,
"self": 3.8799755034633563,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.39522441214649,
"count": 18200,
"is_parallel": true,
"self": 2.39522441214649
},
"communicator.exchange": {
"total": 168.77685234500677,
"count": 18200,
"is_parallel": true,
"self": 168.77685234500677
},
"steps_from_proto": {
"total": 11.960906642685586,
"count": 18200,
"is_parallel": true,
"self": 2.6766800949480967,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.28422654773749,
"count": 182000,
"is_parallel": true,
"self": 9.28422654773749
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.46290058689192e-05,
"count": 1,
"self": 8.46290058689192e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 389.4141271024273,
"count": 344416,
"is_parallel": true,
"self": 6.619416726120107,
"children": {
"process_trajectory": {
"total": 216.45801907726127,
"count": 344416,
"is_parallel": true,
"self": 216.09312064325786,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3648984340034076,
"count": 4,
"is_parallel": true,
"self": 0.3648984340034076
}
}
},
"_update_policy": {
"total": 166.33669129904592,
"count": 90,
"is_parallel": true,
"self": 31.018204163425253,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.31848713562067,
"count": 4587,
"is_parallel": true,
"self": 135.31848713562067
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.059357001999160275,
"count": 1,
"self": 0.0006415859970729798,
"children": {
"RLTrainer._checkpoint": {
"total": 0.058715416002087295,
"count": 1,
"self": 0.058715416002087295
}
}
}
}
}
}
}