dfm794's picture
First training attempt of SnowballTarget
32d943e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9351791739463806,
"min": 0.9085296988487244,
"max": 2.8674800395965576,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8929.0908203125,
"min": 8794.5673828125,
"max": 29365.86328125,
"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": 13.010565757751465,
"min": 0.45316559076309204,
"max": 13.010565757751465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2537.060302734375,
"min": 87.91412353515625,
"max": 2621.1279296875,
"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": 0.07064084658700534,
"min": 0.060282291067529054,
"max": 0.0742608399336984,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28256338634802136,
"min": 0.24112916427011621,
"max": 0.37130419966849204,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2215303261490429,
"min": 0.11848439510989311,
"max": 0.2790162005845238,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8861213045961716,
"min": 0.47393758043957246,
"max": 1.395081002922619,
"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": 25.818181818181817,
"min": 3.4545454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 152.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.4545454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 152.0,
"max": 1414.0,
"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": "1673745735",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673746164"
},
"total": 429.0291111509998,
"count": 1,
"self": 0.38673977400003423,
"children": {
"run_training.setup": {
"total": 0.11066838199985796,
"count": 1,
"self": 0.11066838199985796
},
"TrainerController.start_learning": {
"total": 428.53170299499993,
"count": 1,
"self": 0.5284511209802076,
"children": {
"TrainerController._reset_env": {
"total": 10.089049190999958,
"count": 1,
"self": 10.089049190999958
},
"TrainerController.advance": {
"total": 417.7963976160197,
"count": 18204,
"self": 0.28315442301664007,
"children": {
"env_step": {
"total": 417.51324319300306,
"count": 18204,
"self": 269.3885429509892,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.8590671360016,
"count": 18204,
"self": 1.3718651490146385,
"children": {
"TorchPolicy.evaluate": {
"total": 146.48720198698697,
"count": 18204,
"self": 33.98808186997394,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.49912011701304,
"count": 18204,
"self": 112.49912011701304
}
}
}
}
},
"workers": {
"total": 0.26563310601227386,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.3525419099956,
"count": 18204,
"is_parallel": true,
"self": 208.74108811798214,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010686755000051562,
"count": 1,
"is_parallel": true,
"self": 0.005748475999780567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004938279000270995,
"count": 10,
"is_parallel": true,
"self": 0.004938279000270995
}
}
},
"UnityEnvironment.step": {
"total": 0.04512624899984985,
"count": 1,
"is_parallel": true,
"self": 0.0003098049999152863,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002804409998589108,
"count": 1,
"is_parallel": true,
"self": 0.0002804409998589108
},
"communicator.exchange": {
"total": 0.04343896499995026,
"count": 1,
"is_parallel": true,
"self": 0.04343896499995026
},
"steps_from_proto": {
"total": 0.0010970380001253943,
"count": 1,
"is_parallel": true,
"self": 0.00027151599988428643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008255220002411079,
"count": 10,
"is_parallel": true,
"self": 0.0008255220002411079
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.61145379201344,
"count": 18203,
"is_parallel": true,
"self": 8.545043909005699,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.961915974003205,
"count": 18203,
"is_parallel": true,
"self": 4.961915974003205
},
"communicator.exchange": {
"total": 174.72025372700432,
"count": 18203,
"is_parallel": true,
"self": 174.72025372700432
},
"steps_from_proto": {
"total": 30.384240182000212,
"count": 18203,
"is_parallel": true,
"self": 6.497850900018648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.886389281981565,
"count": 182030,
"is_parallel": true,
"self": 23.886389281981565
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.135399990445876e-05,
"count": 1,
"self": 4.135399990445876e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 414.6268231199615,
"count": 340466,
"is_parallel": true,
"self": 9.460732599019593,
"children": {
"process_trajectory": {
"total": 237.2181891529417,
"count": 340466,
"is_parallel": true,
"self": 236.45411752894165,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7640716240000529,
"count": 4,
"is_parallel": true,
"self": 0.7640716240000529
}
}
},
"_update_policy": {
"total": 167.9479013680002,
"count": 90,
"is_parallel": true,
"self": 42.8831399550038,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.0647614129964,
"count": 4587,
"is_parallel": true,
"self": 125.0647614129964
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11776371300015853,
"count": 1,
"self": 0.0008297330002733361,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1169339799998852,
"count": 1,
"self": 0.1169339799998852
}
}
}
}
}
}
}