peter1133's picture
first commit
c718dbf
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0219413042068481,
"min": 0.9756550192832947,
"max": 2.872624397277832,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9757.4951171875,
"min": 9588.419921875,
"max": 29450.14453125,
"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": 12.433053016662598,
"min": 0.30255573987960815,
"max": 12.433053016662598,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2424.4453125,
"min": 58.6958122253418,
"max": 2502.79541015625,
"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": 0.0704465768352498,
"min": 0.06333370500360616,
"max": 0.07431291298916239,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2817863073409992,
"min": 0.26709307359723267,
"max": 0.3552492259095386,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20869694715913606,
"min": 0.11525977814602026,
"max": 0.27113898712046003,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8347877886365442,
"min": 0.46103911258408103,
"max": 1.3556949356023003,
"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": 24.931818181818183,
"min": 3.0681818181818183,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 135.0,
"max": 1337.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.0681818181818183,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 135.0,
"max": 1337.0,
"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": "1674008167",
"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": "1.21.6",
"end_time_seconds": "1674008605"
},
"total": 438.02230696499987,
"count": 1,
"self": 0.3944130309996581,
"children": {
"run_training.setup": {
"total": 0.10723193000012543,
"count": 1,
"self": 0.10723193000012543
},
"TrainerController.start_learning": {
"total": 437.5206620040001,
"count": 1,
"self": 0.5363552209746558,
"children": {
"TrainerController._reset_env": {
"total": 9.50716274399997,
"count": 1,
"self": 9.50716274399997
},
"TrainerController.advance": {
"total": 427.3561756100253,
"count": 18202,
"self": 0.26585747401736626,
"children": {
"env_step": {
"total": 427.0903181360079,
"count": 18202,
"self": 279.954970747026,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.86151153898982,
"count": 18202,
"self": 1.4048099589940648,
"children": {
"TorchPolicy.evaluate": {
"total": 145.45670157999575,
"count": 18202,
"self": 32.61728005398572,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.83942152601003,
"count": 18202,
"self": 112.83942152601003
}
}
}
}
},
"workers": {
"total": 0.2738358499921105,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.20023532497385,
"count": 18202,
"is_parallel": true,
"self": 211.10621564597045,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007702743999971062,
"count": 1,
"is_parallel": true,
"self": 0.0032546200004617276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004448123999509335,
"count": 10,
"is_parallel": true,
"self": 0.004448123999509335
}
}
},
"UnityEnvironment.step": {
"total": 0.05048390100000688,
"count": 1,
"is_parallel": true,
"self": 0.0003533109997988504,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024371700010306085,
"count": 1,
"is_parallel": true,
"self": 0.00024371700010306085
},
"communicator.exchange": {
"total": 0.04833103100008884,
"count": 1,
"is_parallel": true,
"self": 0.04833103100008884
},
"steps_from_proto": {
"total": 0.0015558420000161277,
"count": 1,
"is_parallel": true,
"self": 0.0004129160001866694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011429259998294583,
"count": 10,
"is_parallel": true,
"self": 0.0011429259998294583
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.0940196790034,
"count": 18201,
"is_parallel": true,
"self": 8.375996477068611,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.06296138602147,
"count": 18201,
"is_parallel": true,
"self": 5.06296138602147
},
"communicator.exchange": {
"total": 178.72277429897736,
"count": 18201,
"is_parallel": true,
"self": 178.72277429897736
},
"steps_from_proto": {
"total": 32.93228751693596,
"count": 18201,
"is_parallel": true,
"self": 6.745757856869204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.186529660066753,
"count": 182010,
"is_parallel": true,
"self": 26.186529660066753
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.6905000090191606e-05,
"count": 1,
"self": 4.6905000090191606e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 424.4156276060646,
"count": 345967,
"is_parallel": true,
"self": 9.183310969161084,
"children": {
"process_trajectory": {
"total": 244.05590144490088,
"count": 345967,
"is_parallel": true,
"self": 243.35846505590098,
"children": {
"RLTrainer._checkpoint": {
"total": 0.697436388999904,
"count": 4,
"is_parallel": true,
"self": 0.697436388999904
}
}
},
"_update_policy": {
"total": 171.17641519200265,
"count": 90,
"is_parallel": true,
"self": 44.20326976000638,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.97314543199627,
"count": 4587,
"is_parallel": true,
"self": 126.97314543199627
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12092152400009581,
"count": 1,
"self": 0.0008413939999627473,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12008013000013307,
"count": 1,
"self": 0.12008013000013307
}
}
}
}
}
}
}