JYC333's picture
First Push
ad5f87a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8525767922401428,
"min": 0.8525767922401428,
"max": 2.8758535385131836,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8140.4033203125,
"min": 8140.4033203125,
"max": 29451.6171875,
"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": 12.866122245788574,
"min": 0.3429628610610962,
"max": 12.87718391418457,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.893798828125,
"min": 66.53479766845703,
"max": 2635.5673828125,
"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": 0.07037216023680087,
"min": 0.06270417244548512,
"max": 0.07458378505672206,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2814886409472035,
"min": 0.2578760798392068,
"max": 0.3707096622275262,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2133693437950284,
"min": 0.12285201402618459,
"max": 0.274020649587699,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8534773751801136,
"min": 0.49140805610473837,
"max": 1.3701032479384951,
"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": 25.727272727272727,
"min": 3.6818181818181817,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 162.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.6818181818181817,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 162.0,
"max": 1394.0,
"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": "1674774039",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674774449"
},
"total": 409.402999121,
"count": 1,
"self": 0.390587412999821,
"children": {
"run_training.setup": {
"total": 0.11436307600001783,
"count": 1,
"self": 0.11436307600001783
},
"TrainerController.start_learning": {
"total": 408.89804863200015,
"count": 1,
"self": 0.5044315390033489,
"children": {
"TrainerController._reset_env": {
"total": 9.096212788000003,
"count": 1,
"self": 9.096212788000003
},
"TrainerController.advance": {
"total": 399.18271135799694,
"count": 18201,
"self": 0.24179872498393706,
"children": {
"env_step": {
"total": 398.940912633013,
"count": 18201,
"self": 260.9326633880148,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.76287051701092,
"count": 18201,
"self": 1.3023642600054472,
"children": {
"TorchPolicy.evaluate": {
"total": 136.46050625700548,
"count": 18201,
"self": 31.40878210900007,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.0517241480054,
"count": 18201,
"self": 105.0517241480054
}
}
}
}
},
"workers": {
"total": 0.24537872798725857,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 407.83826825101596,
"count": 18201,
"is_parallel": true,
"self": 196.57633834301123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009766990999992231,
"count": 1,
"is_parallel": true,
"self": 0.005144728000004761,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00462226299998747,
"count": 10,
"is_parallel": true,
"self": 0.00462226299998747
}
}
},
"UnityEnvironment.step": {
"total": 0.05097771800001283,
"count": 1,
"is_parallel": true,
"self": 0.0003574260000505092,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036212999998497253,
"count": 1,
"is_parallel": true,
"self": 0.00036212999998497253
},
"communicator.exchange": {
"total": 0.04859505399997488,
"count": 1,
"is_parallel": true,
"self": 0.04859505399997488
},
"steps_from_proto": {
"total": 0.0016631080000024667,
"count": 1,
"is_parallel": true,
"self": 0.0004185540000207766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012445539999816901,
"count": 10,
"is_parallel": true,
"self": 0.0012445539999816901
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.26192990800473,
"count": 18200,
"is_parallel": true,
"self": 8.03553864498133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.650351621012419,
"count": 18200,
"is_parallel": true,
"self": 4.650351621012419
},
"communicator.exchange": {
"total": 170.40050208000002,
"count": 18200,
"is_parallel": true,
"self": 170.40050208000002
},
"steps_from_proto": {
"total": 28.17553756201096,
"count": 18200,
"is_parallel": true,
"self": 5.906082577010693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.269454985000266,
"count": 182000,
"is_parallel": true,
"self": 22.269454985000266
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.7152000004425645e-05,
"count": 1,
"self": 3.7152000004425645e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 396.5532632189528,
"count": 317532,
"is_parallel": true,
"self": 8.172168595969197,
"children": {
"process_trajectory": {
"total": 227.18595713398338,
"count": 317532,
"is_parallel": true,
"self": 226.1583146909834,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0276424429999906,
"count": 4,
"is_parallel": true,
"self": 1.0276424429999906
}
}
},
"_update_policy": {
"total": 161.19513748900022,
"count": 90,
"is_parallel": true,
"self": 41.38917715799914,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.80596033100107,
"count": 4584,
"is_parallel": true,
"self": 119.80596033100107
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11465579499986234,
"count": 1,
"self": 0.0008126379998429911,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11384315700001935,
"count": 1,
"self": 0.11384315700001935
}
}
}
}
}
}
}