vpepe2003's picture
First Push
bd1df14 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.975673496723175,
"min": 0.975673496723175,
"max": 2.8738489151000977,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9347.927734375,
"min": 9347.927734375,
"max": 29494.3125,
"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": 12.936042785644531,
"min": 0.2826252281665802,
"max": 12.936042785644531,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2522.5283203125,
"min": 54.82929229736328,
"max": 2620.5224609375,
"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": 0.06719192634787474,
"min": 0.062309001081873656,
"max": 0.07751702360817982,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26876770539149897,
"min": 0.24923600432749463,
"max": 0.38758511804089907,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18953976057031574,
"min": 0.09844764101081618,
"max": 0.2737959743130441,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.758159042281263,
"min": 0.39379056404326473,
"max": 1.3689798715652204,
"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": 25.84090909090909,
"min": 3.0681818181818183,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 135.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.0681818181818183,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 135.0,
"max": 1395.0,
"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": "1707959079",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707959457"
},
"total": 378.0973913119999,
"count": 1,
"self": 0.321223825999823,
"children": {
"run_training.setup": {
"total": 0.05086074899998039,
"count": 1,
"self": 0.05086074899998039
},
"TrainerController.start_learning": {
"total": 377.7253067370001,
"count": 1,
"self": 0.4965183360100127,
"children": {
"TrainerController._reset_env": {
"total": 2.6743734719999566,
"count": 1,
"self": 2.6743734719999566
},
"TrainerController.advance": {
"total": 374.46817800799,
"count": 18202,
"self": 0.2302544609906363,
"children": {
"env_step": {
"total": 374.23792354699935,
"count": 18202,
"self": 257.0585172240088,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.94917880099558,
"count": 18202,
"self": 1.2323828399891,
"children": {
"TorchPolicy.evaluate": {
"total": 115.71679596100648,
"count": 18202,
"self": 115.71679596100648
}
}
},
"workers": {
"total": 0.2302275219949479,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 377.0645613659823,
"count": 18202,
"is_parallel": true,
"self": 187.2023425919832,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022300480000012612,
"count": 1,
"is_parallel": true,
"self": 0.0006397700000206896,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015902779999805716,
"count": 10,
"is_parallel": true,
"self": 0.0015902779999805716
}
}
},
"UnityEnvironment.step": {
"total": 0.027055898999947203,
"count": 1,
"is_parallel": true,
"self": 0.000448115999915899,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002696280000691331,
"count": 1,
"is_parallel": true,
"self": 0.0002696280000691331
},
"communicator.exchange": {
"total": 0.02511956899991219,
"count": 1,
"is_parallel": true,
"self": 0.02511956899991219
},
"steps_from_proto": {
"total": 0.0012185860000499815,
"count": 1,
"is_parallel": true,
"self": 0.0002547430001413886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009638429999085929,
"count": 10,
"is_parallel": true,
"self": 0.0009638429999085929
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 189.86221877399907,
"count": 18201,
"is_parallel": true,
"self": 7.374982942996894,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.779381435005007,
"count": 18201,
"is_parallel": true,
"self": 3.779381435005007
},
"communicator.exchange": {
"total": 155.52780561999862,
"count": 18201,
"is_parallel": true,
"self": 155.52780561999862
},
"steps_from_proto": {
"total": 23.180048775998557,
"count": 18201,
"is_parallel": true,
"self": 4.45738418901999,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.722664586978567,
"count": 182010,
"is_parallel": true,
"self": 18.722664586978567
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001608840000244527,
"count": 1,
"self": 0.0001608840000244527,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 373.65712273794475,
"count": 230907,
"is_parallel": true,
"self": 3.136518993912432,
"children": {
"process_trajectory": {
"total": 212.49254888203177,
"count": 230907,
"is_parallel": true,
"self": 212.00270687803152,
"children": {
"RLTrainer._checkpoint": {
"total": 0.489842004000252,
"count": 4,
"is_parallel": true,
"self": 0.489842004000252
}
}
},
"_update_policy": {
"total": 158.02805486200054,
"count": 90,
"is_parallel": true,
"self": 36.55156828299596,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.47648657900459,
"count": 4587,
"is_parallel": true,
"self": 121.47648657900459
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08607603700011168,
"count": 1,
"self": 0.0009227220002685499,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08515331499984313,
"count": 1,
"self": 0.08515331499984313
}
}
}
}
}
}
}