Joalbom14's picture
First Push
8e6b477 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9503044486045837,
"min": 0.9503044486045837,
"max": 2.8731424808502197,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9104.8671875,
"min": 9104.8671875,
"max": 29487.0625,
"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": 13.028663635253906,
"min": 0.15477506816387177,
"max": 13.028663635253906,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.58935546875,
"min": 30.026363372802734,
"max": 2625.36962890625,
"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": 0.06876736837253418,
"min": 0.06358992690077096,
"max": 0.07707360567934195,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2750694734901367,
"min": 0.25435970760308385,
"max": 0.36595905428597086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2023152819305074,
"min": 0.09434543107408008,
"max": 0.25564814963761495,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8092611277220296,
"min": 0.37738172429632033,
"max": 1.2782407481880749,
"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": 25.772727272727273,
"min": 2.8863636363636362,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 127.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 2.8863636363636362,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 127.0,
"max": 1396.0,
"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": "1714169002",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714169538"
},
"total": 535.9339915559999,
"count": 1,
"self": 0.5429827269999805,
"children": {
"run_training.setup": {
"total": 0.06456060099981187,
"count": 1,
"self": 0.06456060099981187
},
"TrainerController.start_learning": {
"total": 535.3264482280001,
"count": 1,
"self": 0.7582076049789066,
"children": {
"TrainerController._reset_env": {
"total": 2.9442528739996305,
"count": 1,
"self": 2.9442528739996305
},
"TrainerController.advance": {
"total": 531.528231911022,
"count": 18202,
"self": 0.3806976920654961,
"children": {
"env_step": {
"total": 531.1475342189565,
"count": 18202,
"self": 411.70885157099565,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.0459971369678,
"count": 18202,
"self": 1.8448769389815425,
"children": {
"TorchPolicy.evaluate": {
"total": 117.20112019798626,
"count": 18202,
"self": 117.20112019798626
}
}
},
"workers": {
"total": 0.39268551099303295,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 533.6951482809654,
"count": 18202,
"is_parallel": true,
"self": 248.11716115593435,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006079983999825345,
"count": 1,
"is_parallel": true,
"self": 0.004191866999008198,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018881170008171466,
"count": 10,
"is_parallel": true,
"self": 0.0018881170008171466
}
}
},
"UnityEnvironment.step": {
"total": 0.0629494079998949,
"count": 1,
"is_parallel": true,
"self": 0.0008373360001314722,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004662070000449603,
"count": 1,
"is_parallel": true,
"self": 0.0004662070000449603
},
"communicator.exchange": {
"total": 0.059295216999998956,
"count": 1,
"is_parallel": true,
"self": 0.059295216999998956
},
"steps_from_proto": {
"total": 0.002350647999719513,
"count": 1,
"is_parallel": true,
"self": 0.0004617630002030637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018888849995164492,
"count": 10,
"is_parallel": true,
"self": 0.0018888849995164492
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 285.5779871250311,
"count": 18201,
"is_parallel": true,
"self": 13.271744605049662,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.167663124994306,
"count": 18201,
"is_parallel": true,
"self": 7.167663124994306
},
"communicator.exchange": {
"total": 222.05860288600297,
"count": 18201,
"is_parallel": true,
"self": 222.05860288600297
},
"steps_from_proto": {
"total": 43.079976508984146,
"count": 18201,
"is_parallel": true,
"self": 8.380255649103674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.69972085988047,
"count": 182010,
"is_parallel": true,
"self": 34.69972085988047
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017652299993642373,
"count": 1,
"self": 0.00017652299993642373,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 525.1930156489598,
"count": 734494,
"is_parallel": true,
"self": 16.14704862187,
"children": {
"process_trajectory": {
"total": 284.5866995200886,
"count": 734494,
"is_parallel": true,
"self": 283.7611332240872,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8255662960013979,
"count": 4,
"is_parallel": true,
"self": 0.8255662960013979
}
}
},
"_update_policy": {
"total": 224.4592675070012,
"count": 90,
"is_parallel": true,
"self": 64.77356188598651,
"children": {
"TorchPPOOptimizer.update": {
"total": 159.68570562101468,
"count": 4587,
"is_parallel": true,
"self": 159.68570562101468
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09557931499966799,
"count": 1,
"self": 0.0012275819999558735,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09435173299971211,
"count": 1,
"self": 0.09435173299971211
}
}
}
}
}
}
}