harisumant's picture
First Push
d4d2b33
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.903866708278656,
"min": 0.903866708278656,
"max": 2.8646275997161865,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8630.119140625,
"min": 8630.119140625,
"max": 29336.65234375,
"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": 12.892969131469727,
"min": 0.3049318492412567,
"max": 12.941045761108398,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2514.12890625,
"min": 59.156776428222656,
"max": 2631.1015625,
"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": 0.06989904728463586,
"min": 0.06465316688270689,
"max": 0.07345318482390105,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27959618913854345,
"min": 0.25861266753082757,
"max": 0.3539928015225622,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1996944819887479,
"min": 0.11473089953491866,
"max": 0.2878405749067372,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7987779279549916,
"min": 0.45892359813967465,
"max": 1.385870530032644,
"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": 25.272727272727273,
"min": 3.0454545454545454,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 134.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.0454545454545454,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 134.0,
"max": 1412.0,
"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": "1677133340",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677133824"
},
"total": 483.9764126570001,
"count": 1,
"self": 0.4448229789999232,
"children": {
"run_training.setup": {
"total": 0.11668671400002495,
"count": 1,
"self": 0.11668671400002495
},
"TrainerController.start_learning": {
"total": 483.41490296400013,
"count": 1,
"self": 0.6191973920058444,
"children": {
"TrainerController._reset_env": {
"total": 10.337497067000072,
"count": 1,
"self": 10.337497067000072
},
"TrainerController.advance": {
"total": 472.3241308819943,
"count": 18201,
"self": 0.3128833359929786,
"children": {
"env_step": {
"total": 472.0112475460013,
"count": 18201,
"self": 324.52763329800314,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.18368018000467,
"count": 18201,
"self": 1.6010562780081727,
"children": {
"TorchPolicy.evaluate": {
"total": 145.5826239019965,
"count": 18201,
"self": 33.48719663299039,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.09542726900611,
"count": 18201,
"self": 112.09542726900611
}
}
}
}
},
"workers": {
"total": 0.2999340679934903,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 481.75482044900093,
"count": 18201,
"is_parallel": true,
"self": 230.36534137100534,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005656296999973165,
"count": 1,
"is_parallel": true,
"self": 0.004413361999695553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012429350002776118,
"count": 10,
"is_parallel": true,
"self": 0.0012429350002776118
}
}
},
"UnityEnvironment.step": {
"total": 0.06554063999999471,
"count": 1,
"is_parallel": true,
"self": 0.0006077130000221587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004094790000408466,
"count": 1,
"is_parallel": true,
"self": 0.0004094790000408466
},
"communicator.exchange": {
"total": 0.06253800699994372,
"count": 1,
"is_parallel": true,
"self": 0.06253800699994372
},
"steps_from_proto": {
"total": 0.0019854409999879863,
"count": 1,
"is_parallel": true,
"self": 0.0005023049999408613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001483136000047125,
"count": 10,
"is_parallel": true,
"self": 0.001483136000047125
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.3894790779956,
"count": 18200,
"is_parallel": true,
"self": 9.853310274003093,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3780562580002425,
"count": 18200,
"is_parallel": true,
"self": 5.3780562580002425
},
"communicator.exchange": {
"total": 203.50207082999304,
"count": 18200,
"is_parallel": true,
"self": 203.50207082999304
},
"steps_from_proto": {
"total": 32.65604171599921,
"count": 18200,
"is_parallel": true,
"self": 7.342256484976929,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.31378523102228,
"count": 182000,
"is_parallel": true,
"self": 25.31378523102228
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018458899990037025,
"count": 1,
"self": 0.00018458899990037025,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 468.9366597519852,
"count": 420603,
"is_parallel": true,
"self": 10.552223219002599,
"children": {
"process_trajectory": {
"total": 270.1510853679813,
"count": 420603,
"is_parallel": true,
"self": 269.4147864159813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7362989519999701,
"count": 4,
"is_parallel": true,
"self": 0.7362989519999701
}
}
},
"_update_policy": {
"total": 188.2333511650013,
"count": 90,
"is_parallel": true,
"self": 63.4788990170058,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.7544521479955,
"count": 4587,
"is_parallel": true,
"self": 124.7544521479955
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13389303400003882,
"count": 1,
"self": 0.0011013289999937115,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1327917050000451,
"count": 1,
"self": 0.1327917050000451
}
}
}
}
}
}
}