mjkim0928's picture
First Push
cfc77a3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8747802972793579,
"min": 0.8747802972793579,
"max": 2.8627872467041016,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8352.40234375,
"min": 8352.40234375,
"max": 29317.8046875,
"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": 13.152514457702637,
"min": 0.3165854811668396,
"max": 13.152514457702637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2564.740234375,
"min": 61.41758346557617,
"max": 2676.48095703125,
"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": 0.07209102178769938,
"min": 0.06670254431040068,
"max": 0.0744869784934517,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28836408715079753,
"min": 0.2668101772416027,
"max": 0.3615377215156674,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17667470288042927,
"min": 0.11295019783873986,
"max": 0.2668568330068214,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7066988115217171,
"min": 0.45180079135495943,
"max": 1.334284165034107,
"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": 25.795454545454547,
"min": 3.3636363636363638,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 148.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 3.3636363636363638,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 148.0,
"max": 1413.0,
"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": "1738574046",
"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=SnowballTarget13 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738574513"
},
"total": 466.62204599200004,
"count": 1,
"self": 0.43486950599981355,
"children": {
"run_training.setup": {
"total": 0.03042731699997603,
"count": 1,
"self": 0.03042731699997603
},
"TrainerController.start_learning": {
"total": 466.15674916900025,
"count": 1,
"self": 0.5820977289608891,
"children": {
"TrainerController._reset_env": {
"total": 2.032334241999706,
"count": 1,
"self": 2.032334241999706
},
"TrainerController.advance": {
"total": 463.4315250020395,
"count": 18201,
"self": 0.2521387199981291,
"children": {
"env_step": {
"total": 463.1793862820414,
"count": 18201,
"self": 286.9077958130124,
"children": {
"SubprocessEnvManager._take_step": {
"total": 176.01763333803137,
"count": 18201,
"self": 1.4888853380266482,
"children": {
"TorchPolicy.evaluate": {
"total": 174.52874800000473,
"count": 18201,
"self": 174.52874800000473
}
}
},
"workers": {
"total": 0.2539571309976054,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.89597393701433,
"count": 18201,
"is_parallel": true,
"self": 245.05612853097819,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020867120001639705,
"count": 1,
"is_parallel": true,
"self": 0.0006430260004890442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014436859996749263,
"count": 10,
"is_parallel": true,
"self": 0.0014436859996749263
}
}
},
"UnityEnvironment.step": {
"total": 0.037585632000173064,
"count": 1,
"is_parallel": true,
"self": 0.0005535430004783848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004020910000690492,
"count": 1,
"is_parallel": true,
"self": 0.0004020910000690492
},
"communicator.exchange": {
"total": 0.0347175519996199,
"count": 1,
"is_parallel": true,
"self": 0.0347175519996199
},
"steps_from_proto": {
"total": 0.0019124460000057297,
"count": 1,
"is_parallel": true,
"self": 0.00038736200076527894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015250839992404508,
"count": 10,
"is_parallel": true,
"self": 0.0015250839992404508
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.83984540603615,
"count": 18200,
"is_parallel": true,
"self": 9.480130093038042,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.043553193995194,
"count": 18200,
"is_parallel": true,
"self": 5.043553193995194
},
"communicator.exchange": {
"total": 173.35884946702754,
"count": 18200,
"is_parallel": true,
"self": 173.35884946702754
},
"steps_from_proto": {
"total": 31.95731265197537,
"count": 18200,
"is_parallel": true,
"self": 5.913494948805237,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.043817703170134,
"count": 182000,
"is_parallel": true,
"self": 26.043817703170134
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016117199993459508,
"count": 1,
"self": 0.00016117199993459508,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 457.5091192341015,
"count": 715140,
"is_parallel": true,
"self": 14.956503937166417,
"children": {
"process_trajectory": {
"total": 251.68808493293682,
"count": 715140,
"is_parallel": true,
"self": 250.86808145393707,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8200034789997517,
"count": 4,
"is_parallel": true,
"self": 0.8200034789997517
}
}
},
"_update_policy": {
"total": 190.86453036399826,
"count": 90,
"is_parallel": true,
"self": 57.301165198000945,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.5633651659973,
"count": 4587,
"is_parallel": true,
"self": 133.5633651659973
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11063102400021307,
"count": 1,
"self": 0.0009276980003960489,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10970332599981703,
"count": 1,
"self": 0.10970332599981703
}
}
}
}
}
}
}