varevshatyan's picture
snowball target model push
41f55b8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9517666101455688,
"min": 0.9517666101455688,
"max": 2.867572546005249,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9150.2841796875,
"min": 9150.2841796875,
"max": 29398.353515625,
"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": 13.036654472351074,
"min": 0.3701440989971161,
"max": 13.036654472351074,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2542.147705078125,
"min": 71.80795288085938,
"max": 2642.98779296875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06937861491634048,
"min": 0.06139263022450192,
"max": 0.07406291223265797,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2775144596653619,
"min": 0.25391567140126,
"max": 0.37031456116328987,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19307967253467617,
"min": 0.10633065608813992,
"max": 0.27095253911672856,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7723186901387047,
"min": 0.4253226243525597,
"max": 1.3354158719965055,
"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": 25.431818181818183,
"min": 2.7954545454545454,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 123.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 2.7954545454545454,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 123.0,
"max": 1428.0,
"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": "1679667987",
"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": "1679668443"
},
"total": 455.13721575700004,
"count": 1,
"self": 0.6357959090000804,
"children": {
"run_training.setup": {
"total": 0.11564964300001179,
"count": 1,
"self": 0.11564964300001179
},
"TrainerController.start_learning": {
"total": 454.385770205,
"count": 1,
"self": 0.5187281280100251,
"children": {
"TrainerController._reset_env": {
"total": 9.420952145000001,
"count": 1,
"self": 9.420952145000001
},
"TrainerController.advance": {
"total": 444.21402328099,
"count": 18223,
"self": 0.25302843699267896,
"children": {
"env_step": {
"total": 443.9609948439973,
"count": 18223,
"self": 318.9516173229937,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.75407389900255,
"count": 18223,
"self": 2.4128345420000414,
"children": {
"TorchPolicy.evaluate": {
"total": 122.34123935700251,
"count": 18223,
"self": 122.34123935700251
}
}
},
"workers": {
"total": 0.2553036220010654,
"count": 18223,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.7987313809994,
"count": 18223,
"is_parallel": true,
"self": 219.31374154699682,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00479055599998901,
"count": 1,
"is_parallel": true,
"self": 0.0034412600000450766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013492959999439336,
"count": 10,
"is_parallel": true,
"self": 0.0013492959999439336
}
}
},
"UnityEnvironment.step": {
"total": 0.06571130999998331,
"count": 1,
"is_parallel": true,
"self": 0.0005661060000647922,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039146699998582335,
"count": 1,
"is_parallel": true,
"self": 0.00039146699998582335
},
"communicator.exchange": {
"total": 0.06296781499997905,
"count": 1,
"is_parallel": true,
"self": 0.06296781499997905
},
"steps_from_proto": {
"total": 0.0017859219999536435,
"count": 1,
"is_parallel": true,
"self": 0.00036665099992205796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014192710000315856,
"count": 10,
"is_parallel": true,
"self": 0.0014192710000315856
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.4849898340026,
"count": 18222,
"is_parallel": true,
"self": 9.351016440990577,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.152797327996211,
"count": 18222,
"is_parallel": true,
"self": 5.152797327996211
},
"communicator.exchange": {
"total": 188.767086494005,
"count": 18222,
"is_parallel": true,
"self": 188.767086494005
},
"steps_from_proto": {
"total": 30.21408957101079,
"count": 18222,
"is_parallel": true,
"self": 5.87366294801069,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.3404266230001,
"count": 182220,
"is_parallel": true,
"self": 24.3404266230001
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012645599997540558,
"count": 1,
"self": 0.00012645599997540558,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.90962763898614,
"count": 398175,
"is_parallel": true,
"self": 9.57504621399977,
"children": {
"process_trajectory": {
"total": 243.7846478229862,
"count": 398175,
"is_parallel": true,
"self": 242.47748529798622,
"children": {
"RLTrainer._checkpoint": {
"total": 1.307162524999967,
"count": 4,
"is_parallel": true,
"self": 1.307162524999967
}
}
},
"_update_policy": {
"total": 187.54993360200018,
"count": 90,
"is_parallel": true,
"self": 68.19294550199874,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.35698810000144,
"count": 4587,
"is_parallel": true,
"self": 119.35698810000144
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23194019499999285,
"count": 1,
"self": 0.0011224350000702543,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2308177599999226,
"count": 1,
"self": 0.2308177599999226
}
}
}
}
}
}
}