fermaat's picture
SnowballTarget1 first attempt
e40e994
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9398490190505981,
"min": 0.9398490190505981,
"max": 2.8557207584381104,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8973.6787109375,
"min": 8973.6787109375,
"max": 29245.4375,
"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": 12.537705421447754,
"min": 0.35438787937164307,
"max": 12.679742813110352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2444.8525390625,
"min": 68.75125122070312,
"max": 2586.66748046875,
"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": 0.07017835005236145,
"min": 0.06272474699525285,
"max": 0.07305320821812047,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2807134002094458,
"min": 0.26330049558829144,
"max": 0.3652660410906024,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23232102218796227,
"min": 0.10541495629677586,
"max": 0.30141540324571087,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9292840887518491,
"min": 0.42165982518710343,
"max": 1.411380719904806,
"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": 24.568181818181817,
"min": 3.0,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1081.0,
"min": 132.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.568181818181817,
"min": 3.0,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1081.0,
"min": 132.0,
"max": 1375.0,
"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": "1675361455",
"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": "1675361867"
},
"total": 411.75159499800003,
"count": 1,
"self": 0.3803127770000856,
"children": {
"run_training.setup": {
"total": 0.09860367299995687,
"count": 1,
"self": 0.09860367299995687
},
"TrainerController.start_learning": {
"total": 411.272678548,
"count": 1,
"self": 0.4793539699977032,
"children": {
"TrainerController._reset_env": {
"total": 9.245068498000023,
"count": 1,
"self": 9.245068498000023
},
"TrainerController.advance": {
"total": 401.43565427000226,
"count": 18200,
"self": 0.24611390800282607,
"children": {
"env_step": {
"total": 401.18954036199943,
"count": 18200,
"self": 261.89021381499595,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.05623397400257,
"count": 18200,
"self": 1.367779479005776,
"children": {
"TorchPolicy.evaluate": {
"total": 137.6884544949968,
"count": 18200,
"self": 30.819969884991565,
"children": {
"TorchPolicy.sample_actions": {
"total": 106.86848461000523,
"count": 18200,
"self": 106.86848461000523
}
}
}
}
},
"workers": {
"total": 0.24309257300092213,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 410.0540351079997,
"count": 18200,
"is_parallel": true,
"self": 197.97727050500106,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005209884000009879,
"count": 1,
"is_parallel": true,
"self": 0.0028942850000248654,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023155989999850135,
"count": 10,
"is_parallel": true,
"self": 0.0023155989999850135
}
}
},
"UnityEnvironment.step": {
"total": 0.031132253999999193,
"count": 1,
"is_parallel": true,
"self": 0.0005102710000528532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000275429999987864,
"count": 1,
"is_parallel": true,
"self": 0.000275429999987864
},
"communicator.exchange": {
"total": 0.028357029999938277,
"count": 1,
"is_parallel": true,
"self": 0.028357029999938277
},
"steps_from_proto": {
"total": 0.001989523000020199,
"count": 1,
"is_parallel": true,
"self": 0.000565298999845254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001424224000174945,
"count": 10,
"is_parallel": true,
"self": 0.001424224000174945
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.07676460299865,
"count": 18199,
"is_parallel": true,
"self": 8.014993773001152,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.769051146997413,
"count": 18199,
"is_parallel": true,
"self": 4.769051146997413
},
"communicator.exchange": {
"total": 170.61660211200228,
"count": 18199,
"is_parallel": true,
"self": 170.61660211200228
},
"steps_from_proto": {
"total": 28.676117570997803,
"count": 18199,
"is_parallel": true,
"self": 6.115253752973331,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.560863818024472,
"count": 181990,
"is_parallel": true,
"self": 22.560863818024472
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.799399996751163e-05,
"count": 1,
"self": 3.799399996751163e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 398.50548080100975,
"count": 336801,
"is_parallel": true,
"self": 8.721175609002671,
"children": {
"process_trajectory": {
"total": 228.9051795990074,
"count": 336801,
"is_parallel": true,
"self": 228.2284914160076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6766881829997828,
"count": 4,
"is_parallel": true,
"self": 0.6766881829997828
}
}
},
"_update_policy": {
"total": 160.87912559299969,
"count": 90,
"is_parallel": true,
"self": 41.01370979900389,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.8654157939958,
"count": 4587,
"is_parallel": true,
"self": 119.8654157939958
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11256381600003351,
"count": 1,
"self": 0.0009290899999996327,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11163472600003388,
"count": 1,
"self": 0.11163472600003388
}
}
}
}
}
}
}