lzacchini's picture
First Push of snowball model
ee7bada verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8471393585205078,
"min": 0.8399691581726074,
"max": 2.861318588256836,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8088.48681640625,
"min": 8088.48681640625,
"max": 29334.23828125,
"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": 13.124927520751953,
"min": 0.4393238127231598,
"max": 13.124927520751953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.36083984375,
"min": 85.22882080078125,
"max": 2659.8251953125,
"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": 0.06693383388583066,
"min": 0.0625337530195704,
"max": 0.07200581618201206,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26773533554332263,
"min": 0.2549311100626844,
"max": 0.3600290809100603,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2008234107611226,
"min": 0.13508233727485525,
"max": 0.2809308783096426,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8032936430444904,
"min": 0.540329349099421,
"max": 1.4046543915482128,
"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": 25.795454545454547,
"min": 4.090909090909091,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 180.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 4.090909090909091,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 180.0,
"max": 1421.0,
"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": "1714569422",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714569879"
},
"total": 456.7507167000001,
"count": 1,
"self": 0.43350473800001055,
"children": {
"run_training.setup": {
"total": 0.056465275999926234,
"count": 1,
"self": 0.056465275999926234
},
"TrainerController.start_learning": {
"total": 456.2607466860002,
"count": 1,
"self": 0.5495188799845891,
"children": {
"TrainerController._reset_env": {
"total": 2.63788945400006,
"count": 1,
"self": 2.63788945400006
},
"TrainerController.advance": {
"total": 452.9633919940154,
"count": 18199,
"self": 0.27081156001759155,
"children": {
"env_step": {
"total": 452.6925804339978,
"count": 18199,
"self": 295.065938288006,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.33712419501217,
"count": 18199,
"self": 1.4915400510021755,
"children": {
"TorchPolicy.evaluate": {
"total": 155.84558414401,
"count": 18199,
"self": 155.84558414401
}
}
},
"workers": {
"total": 0.2895179509796435,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.0005788540011,
"count": 18199,
"is_parallel": true,
"self": 229.8613661759946,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005055732000073476,
"count": 1,
"is_parallel": true,
"self": 0.0035175049995359586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015382270005375176,
"count": 10,
"is_parallel": true,
"self": 0.0015382270005375176
}
}
},
"UnityEnvironment.step": {
"total": 0.037725786000009975,
"count": 1,
"is_parallel": true,
"self": 0.0008079929998530133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038739800015719084,
"count": 1,
"is_parallel": true,
"self": 0.00038739800015719084
},
"communicator.exchange": {
"total": 0.03446220799992261,
"count": 1,
"is_parallel": true,
"self": 0.03446220799992261
},
"steps_from_proto": {
"total": 0.0020681870000771596,
"count": 1,
"is_parallel": true,
"self": 0.00038196500031517644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016862219997619832,
"count": 10,
"is_parallel": true,
"self": 0.0016862219997619832
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.13921267800652,
"count": 18198,
"is_parallel": true,
"self": 10.298323922016152,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.502745997993998,
"count": 18198,
"is_parallel": true,
"self": 5.502745997993998
},
"communicator.exchange": {
"total": 174.78305886498902,
"count": 18198,
"is_parallel": true,
"self": 174.78305886498902
},
"steps_from_proto": {
"total": 34.55508389300735,
"count": 18198,
"is_parallel": true,
"self": 6.480612380916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.07447151209135,
"count": 181980,
"is_parallel": true,
"self": 28.07447151209135
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016005900010895857,
"count": 1,
"self": 0.00016005900010895857,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.26902669104106,
"count": 673700,
"is_parallel": true,
"self": 14.60782488597988,
"children": {
"process_trajectory": {
"total": 245.7023922730607,
"count": 673700,
"is_parallel": true,
"self": 245.0494965170608,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6528957559999071,
"count": 4,
"is_parallel": true,
"self": 0.6528957559999071
}
}
},
"_update_policy": {
"total": 186.9588095320005,
"count": 90,
"is_parallel": true,
"self": 52.97480697799665,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.98400255400384,
"count": 4587,
"is_parallel": true,
"self": 133.98400255400384
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10978629900000669,
"count": 1,
"self": 0.0012380260000099952,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1085482729999967,
"count": 1,
"self": 0.1085482729999967
}
}
}
}
}
}
}