Miltomo's picture
First Push
170fcee verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0494744777679443,
"min": 1.0494744777679443,
"max": 2.865435838699341,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10020.3818359375,
"min": 10020.3818359375,
"max": 29376.44921875,
"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": 12.391914367675781,
"min": 0.3041415810585022,
"max": 12.391914367675781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2416.42333984375,
"min": 59.00346755981445,
"max": 2494.83203125,
"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": 0.06286303321579836,
"min": 0.06286303321579836,
"max": 0.08093349305408101,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25145213286319346,
"min": 0.25145213286319346,
"max": 0.3807446599005512,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21280553520602338,
"min": 0.12705359701409608,
"max": 0.27461110778591213,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8512221408240935,
"min": 0.5082143880563843,
"max": 1.3545678255933464,
"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": 24.772727272727273,
"min": 3.3636363636363638,
"max": 24.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 148.0,
"max": 1339.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.3636363636363638,
"max": 24.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 148.0,
"max": 1339.0,
"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": "1712903424",
"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": "1712903866"
},
"total": 442.343190822,
"count": 1,
"self": 0.4389002560001245,
"children": {
"run_training.setup": {
"total": 0.05559814799994456,
"count": 1,
"self": 0.05559814799994456
},
"TrainerController.start_learning": {
"total": 441.8486924179999,
"count": 1,
"self": 0.5454603500145367,
"children": {
"TrainerController._reset_env": {
"total": 3.1679222600000685,
"count": 1,
"self": 3.1679222600000685
},
"TrainerController.advance": {
"total": 438.0417438859854,
"count": 18199,
"self": 0.2489628129749235,
"children": {
"env_step": {
"total": 437.7927810730105,
"count": 18199,
"self": 282.7202697679677,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.79898634001597,
"count": 18199,
"self": 1.4134832800255026,
"children": {
"TorchPolicy.evaluate": {
"total": 153.38550305999047,
"count": 18199,
"self": 153.38550305999047
}
}
},
"workers": {
"total": 0.2735249650268088,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.75553935801304,
"count": 18199,
"is_parallel": true,
"self": 220.30432962599502,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008083315000021685,
"count": 1,
"is_parallel": true,
"self": 0.006431239999528771,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016520750004929141,
"count": 10,
"is_parallel": true,
"self": 0.0016520750004929141
}
}
},
"UnityEnvironment.step": {
"total": 0.04254243899981702,
"count": 1,
"is_parallel": true,
"self": 0.0007120519999261887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048731500010035234,
"count": 1,
"is_parallel": true,
"self": 0.00048731500010035234
},
"communicator.exchange": {
"total": 0.039383957999916674,
"count": 1,
"is_parallel": true,
"self": 0.039383957999916674
},
"steps_from_proto": {
"total": 0.001959113999873807,
"count": 1,
"is_parallel": true,
"self": 0.0003897329995652399,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015693810003085673,
"count": 10,
"is_parallel": true,
"self": 0.0015693810003085673
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.45120973201801,
"count": 18198,
"is_parallel": true,
"self": 10.204631780046157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.259691207984815,
"count": 18198,
"is_parallel": true,
"self": 5.259691207984815
},
"communicator.exchange": {
"total": 171.94043819598187,
"count": 18198,
"is_parallel": true,
"self": 171.94043819598187
},
"steps_from_proto": {
"total": 33.04644854800517,
"count": 18198,
"is_parallel": true,
"self": 6.1029539090002345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.94349463900494,
"count": 181980,
"is_parallel": true,
"self": 26.94349463900494
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012160799997218419,
"count": 1,
"self": 0.00012160799997218419,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 432.3431129629064,
"count": 658051,
"is_parallel": true,
"self": 14.111028134948128,
"children": {
"process_trajectory": {
"total": 237.65341989895842,
"count": 658051,
"is_parallel": true,
"self": 236.77097883295846,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8824410659999558,
"count": 4,
"is_parallel": true,
"self": 0.8824410659999558
}
}
},
"_update_policy": {
"total": 180.57866492899984,
"count": 90,
"is_parallel": true,
"self": 51.14104813800168,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.43761679099816,
"count": 4581,
"is_parallel": true,
"self": 129.43761679099816
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09344431399995301,
"count": 1,
"self": 0.0009363619999476214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09250795200000539,
"count": 1,
"self": 0.09250795200000539
}
}
}
}
}
}
}