lenant's picture
First Push
906c452 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9141303300857544,
"min": 0.9141303300857544,
"max": 2.8624210357666016,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8748.2275390625,
"min": 8748.2275390625,
"max": 29314.0546875,
"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": 12.940289497375488,
"min": 0.36126571893692017,
"max": 12.940289497375488,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.3564453125,
"min": 70.0855484008789,
"max": 2612.939453125,
"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": 0.07196958720919165,
"min": 0.06162835245682871,
"max": 0.07275290445506791,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2878783488367666,
"min": 0.24651340982731484,
"max": 0.36376452227533956,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19214857442706237,
"min": 0.1379099031042892,
"max": 0.2833534146640815,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7685942977082495,
"min": 0.5516396124171568,
"max": 1.4167670733204074,
"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": 25.522727272727273,
"min": 3.9545454545454546,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 174.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 3.9545454545454546,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 174.0,
"max": 1405.0,
"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": "1722727752",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722728233"
},
"total": 480.9374621280001,
"count": 1,
"self": 0.4376311279999072,
"children": {
"run_training.setup": {
"total": 0.062494146000062756,
"count": 1,
"self": 0.062494146000062756
},
"TrainerController.start_learning": {
"total": 480.43733685400014,
"count": 1,
"self": 0.6475789889929047,
"children": {
"TrainerController._reset_env": {
"total": 2.7956334949999473,
"count": 1,
"self": 2.7956334949999473
},
"TrainerController.advance": {
"total": 476.90259570600733,
"count": 18202,
"self": 0.30164573501861014,
"children": {
"env_step": {
"total": 476.6009499709887,
"count": 18202,
"self": 310.61005931300815,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.68519844299055,
"count": 18202,
"self": 1.6075925739853574,
"children": {
"TorchPolicy.evaluate": {
"total": 164.0776058690052,
"count": 18202,
"self": 164.0776058690052
}
}
},
"workers": {
"total": 0.3056922149900174,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 478.9540662310103,
"count": 18202,
"is_parallel": true,
"self": 241.9032674140086,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005700032999925497,
"count": 1,
"is_parallel": true,
"self": 0.004047453999874051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016525790000514462,
"count": 10,
"is_parallel": true,
"self": 0.0016525790000514462
}
}
},
"UnityEnvironment.step": {
"total": 0.04377807200000916,
"count": 1,
"is_parallel": true,
"self": 0.0007966160000023592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004651200000580502,
"count": 1,
"is_parallel": true,
"self": 0.0004651200000580502
},
"communicator.exchange": {
"total": 0.040101095999943936,
"count": 1,
"is_parallel": true,
"self": 0.040101095999943936
},
"steps_from_proto": {
"total": 0.0024152400000048146,
"count": 1,
"is_parallel": true,
"self": 0.0004319240000540958,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001983315999950719,
"count": 10,
"is_parallel": true,
"self": 0.001983315999950719
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.0507988170017,
"count": 18201,
"is_parallel": true,
"self": 10.64845192800874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.594305211993401,
"count": 18201,
"is_parallel": true,
"self": 5.594305211993401
},
"communicator.exchange": {
"total": 185.16357223099703,
"count": 18201,
"is_parallel": true,
"self": 185.16357223099703
},
"steps_from_proto": {
"total": 35.64446944600252,
"count": 18201,
"is_parallel": true,
"self": 6.863644891967397,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.78082455403512,
"count": 182010,
"is_parallel": true,
"self": 28.78082455403512
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001303900000948488,
"count": 1,
"self": 0.0001303900000948488,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.7812232779845,
"count": 715005,
"is_parallel": true,
"self": 15.384205609996002,
"children": {
"process_trajectory": {
"total": 261.49195132398836,
"count": 715005,
"is_parallel": true,
"self": 260.5177785519885,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9741727719998607,
"count": 4,
"is_parallel": true,
"self": 0.9741727719998607
}
}
},
"_update_policy": {
"total": 193.90506634400015,
"count": 90,
"is_parallel": true,
"self": 61.53562275400077,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.36944358999938,
"count": 4587,
"is_parallel": true,
"self": 132.36944358999938
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09139827399985734,
"count": 1,
"self": 0.0009539559998756886,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09044431799998165,
"count": 1,
"self": 0.09044431799998165
}
}
}
}
}
}
}