RayanRen's picture
First Push
cff671e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1373432874679565,
"min": 1.1373432874679565,
"max": 2.8704631328582764,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10871.8642578125,
"min": 10871.8642578125,
"max": 29427.98828125,
"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": 12.541611671447754,
"min": 0.4222339689731598,
"max": 12.541611671447754,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2445.6142578125,
"min": 81.91339111328125,
"max": 2528.705078125,
"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": 0.0677396163787218,
"min": 0.06015620082429201,
"max": 0.0782644550017008,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2709584655148872,
"min": 0.24062480329716804,
"max": 0.39132227500850403,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20351290900041075,
"min": 0.11428337070666364,
"max": 0.2746093627868914,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.814051636001643,
"min": 0.45713348282665456,
"max": 1.3730468139344572,
"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": 24.613636363636363,
"min": 3.3181818181818183,
"max": 25.12727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 146.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 3.3181818181818183,
"max": 25.12727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 146.0,
"max": 1382.0,
"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": "1697490362",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697490837"
},
"total": 474.759544497,
"count": 1,
"self": 0.42458644599997797,
"children": {
"run_training.setup": {
"total": 0.07360965300000544,
"count": 1,
"self": 0.07360965300000544
},
"TrainerController.start_learning": {
"total": 474.261348398,
"count": 1,
"self": 0.5450436619959191,
"children": {
"TrainerController._reset_env": {
"total": 7.059141660000023,
"count": 1,
"self": 7.059141660000023
},
"TrainerController.advance": {
"total": 466.56192932100396,
"count": 18201,
"self": 0.27409702100294453,
"children": {
"env_step": {
"total": 466.287832300001,
"count": 18201,
"self": 318.8800419859948,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.1189198280079,
"count": 18201,
"self": 1.4500097530169,
"children": {
"TorchPolicy.evaluate": {
"total": 145.668910074991,
"count": 18201,
"self": 145.668910074991
}
}
},
"workers": {
"total": 0.28887048599830223,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.9340079890026,
"count": 18201,
"is_parallel": true,
"self": 230.07712771800084,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005356211999981042,
"count": 1,
"is_parallel": true,
"self": 0.003372838000018419,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001983373999962623,
"count": 10,
"is_parallel": true,
"self": 0.001983373999962623
}
}
},
"UnityEnvironment.step": {
"total": 0.03522824899999932,
"count": 1,
"is_parallel": true,
"self": 0.0007208179999338427,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040965400000914087,
"count": 1,
"is_parallel": true,
"self": 0.00040965400000914087
},
"communicator.exchange": {
"total": 0.031602736000024834,
"count": 1,
"is_parallel": true,
"self": 0.031602736000024834
},
"steps_from_proto": {
"total": 0.002495041000031506,
"count": 1,
"is_parallel": true,
"self": 0.0006134860000202025,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018815550000113035,
"count": 10,
"is_parallel": true,
"self": 0.0018815550000113035
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.85688027100178,
"count": 18200,
"is_parallel": true,
"self": 10.720388531007245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.592365843006348,
"count": 18200,
"is_parallel": true,
"self": 5.592365843006348
},
"communicator.exchange": {
"total": 191.1688312809933,
"count": 18200,
"is_parallel": true,
"self": 191.1688312809933
},
"steps_from_proto": {
"total": 35.3752946159949,
"count": 18200,
"is_parallel": true,
"self": 6.582828770997764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.79246584499714,
"count": 182000,
"is_parallel": true,
"self": 28.79246584499714
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011487200004012266,
"count": 1,
"self": 0.00011487200004012266,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.670223796982,
"count": 479016,
"is_parallel": true,
"self": 10.570972540012178,
"children": {
"process_trajectory": {
"total": 261.39194231597014,
"count": 479016,
"is_parallel": true,
"self": 260.69658895497014,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6953533610000022,
"count": 4,
"is_parallel": true,
"self": 0.6953533610000022
}
}
},
"_update_policy": {
"total": 190.70730894099967,
"count": 90,
"is_parallel": true,
"self": 61.20711774999734,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.50019119100233,
"count": 4584,
"is_parallel": true,
"self": 129.50019119100233
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09511888300005467,
"count": 1,
"self": 0.0009136970001009104,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09420518599995376,
"count": 1,
"self": 0.09420518599995376
}
}
}
}
}
}
}