luozuolin's picture
First Push
1701aae verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0668340921401978,
"min": 1.0668340921401978,
"max": 2.8449485301971436,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10233.072265625,
"min": 10233.072265625,
"max": 29229.001953125,
"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": 12.904620170593262,
"min": 0.3081861734390259,
"max": 12.904620170593262,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2516.40087890625,
"min": 59.788116455078125,
"max": 2609.12255859375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06639417334575709,
"min": 0.05930793652363469,
"max": 0.07352525546716518,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26557669338302836,
"min": 0.23723174609453876,
"max": 0.36762627733582587,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20387273376771048,
"min": 0.137935274344522,
"max": 0.27149863523595474,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8154909350708419,
"min": 0.551741097378088,
"max": 1.3574931761797737,
"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": 25.477272727272727,
"min": 3.75,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 165.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.75,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 165.0,
"max": 1399.0,
"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": "1765352015",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765352715"
},
"total": 699.748814966,
"count": 1,
"self": 0.591341822000004,
"children": {
"run_training.setup": {
"total": 0.04169700600004944,
"count": 1,
"self": 0.04169700600004944
},
"TrainerController.start_learning": {
"total": 699.115776138,
"count": 1,
"self": 0.9145947960003014,
"children": {
"TrainerController._reset_env": {
"total": 3.9029731409998476,
"count": 1,
"self": 3.9029731409998476
},
"TrainerController.advance": {
"total": 694.2247975529997,
"count": 18206,
"self": 0.4669889359759054,
"children": {
"env_step": {
"total": 693.7578086170238,
"count": 18206,
"self": 561.9175539990031,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.39461879302166,
"count": 18206,
"self": 2.113456145011014,
"children": {
"TorchPolicy.evaluate": {
"total": 129.28116264801065,
"count": 18206,
"self": 129.28116264801065
}
}
},
"workers": {
"total": 0.4456358249990444,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 695.7908903700152,
"count": 18206,
"is_parallel": true,
"self": 285.8173293820123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005868941000017003,
"count": 1,
"is_parallel": true,
"self": 0.003611988999409732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022569520006072707,
"count": 10,
"is_parallel": true,
"self": 0.0022569520006072707
}
}
},
"UnityEnvironment.step": {
"total": 0.043267079000088415,
"count": 1,
"is_parallel": true,
"self": 0.0006975060000513622,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042484799996600486,
"count": 1,
"is_parallel": true,
"self": 0.00042484799996600486
},
"communicator.exchange": {
"total": 0.039872500999990734,
"count": 1,
"is_parallel": true,
"self": 0.039872500999990734
},
"steps_from_proto": {
"total": 0.002272224000080314,
"count": 1,
"is_parallel": true,
"self": 0.00042592800036800327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018462959997123107,
"count": 10,
"is_parallel": true,
"self": 0.0018462959997123107
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 409.9735609880029,
"count": 18205,
"is_parallel": true,
"self": 17.952043050015618,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.449513713988381,
"count": 18205,
"is_parallel": true,
"self": 8.449513713988381
},
"communicator.exchange": {
"total": 321.3058140340015,
"count": 18205,
"is_parallel": true,
"self": 321.3058140340015
},
"steps_from_proto": {
"total": 62.26619018999736,
"count": 18205,
"is_parallel": true,
"self": 12.320028577001722,
"children": {
"_process_rank_one_or_two_observation": {
"total": 49.94616161299564,
"count": 182050,
"is_parallel": true,
"self": 49.94616161299564
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012771800015798362,
"count": 1,
"self": 0.00012771800015798362,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 690.8646459740257,
"count": 384999,
"is_parallel": true,
"self": 10.464967322114717,
"children": {
"process_trajectory": {
"total": 386.922159306911,
"count": 384999,
"is_parallel": true,
"self": 385.9591093729109,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9630499340000824,
"count": 4,
"is_parallel": true,
"self": 0.9630499340000824
}
}
},
"_update_policy": {
"total": 293.477519345,
"count": 90,
"is_parallel": true,
"self": 60.249042276990394,
"children": {
"TorchPPOOptimizer.update": {
"total": 233.22847706800962,
"count": 4587,
"is_parallel": true,
"self": 233.22847706800962
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07328293000000485,
"count": 1,
"self": 0.0009152259999609669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07236770400004389,
"count": 1,
"self": 0.07236770400004389
}
}
}
}
}
}
}