splusminusx's picture
Initial commit
307bafb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.914595901966095,
"min": 0.914595901966095,
"max": 2.8716745376586914,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8732.5615234375,
"min": 8732.5615234375,
"max": 29471.99609375,
"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": 11.72767162322998,
"min": 0.393268346786499,
"max": 11.72767162322998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2286.89599609375,
"min": 76.29405975341797,
"max": 2362.4765625,
"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": 0.07126078553276374,
"min": 0.06240441182383211,
"max": 0.07730100708990814,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28504314213105497,
"min": 0.268688241594503,
"max": 0.38650503544954073,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1856529988421529,
"min": 0.1274306614376495,
"max": 0.2839661006103543,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7426119953686116,
"min": 0.509722645750598,
"max": 1.3914294292529426,
"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": 23.272727272727273,
"min": 3.5454545454545454,
"max": 23.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1024.0,
"min": 156.0,
"max": 1270.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.272727272727273,
"min": 3.5454545454545454,
"max": 23.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1024.0,
"min": 156.0,
"max": 1270.0,
"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": "1679058516",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679058990"
},
"total": 473.43599593099987,
"count": 1,
"self": 0.4392321999998785,
"children": {
"run_training.setup": {
"total": 0.15079428100000314,
"count": 1,
"self": 0.15079428100000314
},
"TrainerController.start_learning": {
"total": 472.84596945,
"count": 1,
"self": 0.5993287239991787,
"children": {
"TrainerController._reset_env": {
"total": 9.453146441999934,
"count": 1,
"self": 9.453146441999934
},
"TrainerController.advance": {
"total": 462.660528648001,
"count": 18201,
"self": 0.3173638639948422,
"children": {
"env_step": {
"total": 462.34316478400615,
"count": 18201,
"self": 334.347645047009,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.70240032599395,
"count": 18201,
"self": 2.1274474719908767,
"children": {
"TorchPolicy.evaluate": {
"total": 125.57495285400307,
"count": 18201,
"self": 125.57495285400307
}
}
},
"workers": {
"total": 0.2931194110032038,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.13463177599806,
"count": 18201,
"is_parallel": true,
"self": 223.8982399260068,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0063699559999577104,
"count": 1,
"is_parallel": true,
"self": 0.004217104000076688,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021528519998810225,
"count": 10,
"is_parallel": true,
"self": 0.0021528519998810225
}
}
},
"UnityEnvironment.step": {
"total": 0.03490070899999864,
"count": 1,
"is_parallel": true,
"self": 0.0005612510001355986,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029561499991359597,
"count": 1,
"is_parallel": true,
"self": 0.00029561499991359597
},
"communicator.exchange": {
"total": 0.031868867999946815,
"count": 1,
"is_parallel": true,
"self": 0.031868867999946815
},
"steps_from_proto": {
"total": 0.0021749750000026324,
"count": 1,
"is_parallel": true,
"self": 0.000508159999981217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016668150000214155,
"count": 10,
"is_parallel": true,
"self": 0.0016668150000214155
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.23639184999126,
"count": 18200,
"is_parallel": true,
"self": 9.77127641599634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.264521023990369,
"count": 18200,
"is_parallel": true,
"self": 5.264521023990369
},
"communicator.exchange": {
"total": 200.50361726900735,
"count": 18200,
"is_parallel": true,
"self": 200.50361726900735
},
"steps_from_proto": {
"total": 31.696977140997205,
"count": 18200,
"is_parallel": true,
"self": 6.502781344035611,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.194195796961594,
"count": 182000,
"is_parallel": true,
"self": 25.194195796961594
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000123871999903713,
"count": 1,
"self": 0.000123871999903713,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.2584421149826,
"count": 407360,
"is_parallel": true,
"self": 10.050806410926612,
"children": {
"process_trajectory": {
"total": 255.8264781800558,
"count": 407360,
"is_parallel": true,
"self": 254.3660271730555,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4604510070003016,
"count": 4,
"is_parallel": true,
"self": 1.4604510070003016
}
}
},
"_update_policy": {
"total": 193.38115752400017,
"count": 90,
"is_parallel": true,
"self": 69.26468630499414,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.11647121900603,
"count": 4587,
"is_parallel": true,
"self": 124.11647121900603
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13284176399997705,
"count": 1,
"self": 0.0008693149998180161,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13197244900015903,
"count": 1,
"self": 0.13197244900015903
}
}
}
}
}
}
}