MLIsaac's picture
First Push
524ac87 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8198138475418091,
"min": 0.8198138475418091,
"max": 2.8642821311950684,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7836.6005859375,
"min": 7836.6005859375,
"max": 29333.11328125,
"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": 12.563416481018066,
"min": 0.4786704182624817,
"max": 12.563416481018066,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2449.8662109375,
"min": 92.862060546875,
"max": 2558.66064453125,
"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": 0.06505748430950631,
"min": 0.05854827283529077,
"max": 0.07271858605007783,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26022993723802523,
"min": 0.24006888531542192,
"max": 0.356764364604126,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17804621945263124,
"min": 0.137103978884589,
"max": 0.2906308392683665,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.712184877810525,
"min": 0.548415915538356,
"max": 1.4531541963418326,
"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": 25.636363636363637,
"min": 4.0,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 176.0,
"max": 1369.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 4.0,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 176.0,
"max": 1369.0,
"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": "1713392506",
"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": "1713392951"
},
"total": 444.229076668,
"count": 1,
"self": 0.43896383900005276,
"children": {
"run_training.setup": {
"total": 0.05243440599997484,
"count": 1,
"self": 0.05243440599997484
},
"TrainerController.start_learning": {
"total": 443.737678423,
"count": 1,
"self": 0.5425659250005879,
"children": {
"TrainerController._reset_env": {
"total": 3.090444242999979,
"count": 1,
"self": 3.090444242999979
},
"TrainerController.advance": {
"total": 439.9984748699994,
"count": 18200,
"self": 0.24947169299753114,
"children": {
"env_step": {
"total": 439.7490031770019,
"count": 18200,
"self": 285.67912739300624,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.79407448099755,
"count": 18200,
"self": 1.434613517991579,
"children": {
"TorchPolicy.evaluate": {
"total": 152.35946096300597,
"count": 18200,
"self": 152.35946096300597
}
}
},
"workers": {
"total": 0.27580130299810435,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.5717014639918,
"count": 18200,
"is_parallel": true,
"self": 223.8889489699912,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005480917999989288,
"count": 1,
"is_parallel": true,
"self": 0.0038709550000248782,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016099629999644094,
"count": 10,
"is_parallel": true,
"self": 0.0016099629999644094
}
}
},
"UnityEnvironment.step": {
"total": 0.08104464400003053,
"count": 1,
"is_parallel": true,
"self": 0.0006364350000467311,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042511300000569463,
"count": 1,
"is_parallel": true,
"self": 0.00042511300000569463
},
"communicator.exchange": {
"total": 0.07807983800000784,
"count": 1,
"is_parallel": true,
"self": 0.07807983800000784
},
"steps_from_proto": {
"total": 0.0019032579999702648,
"count": 1,
"is_parallel": true,
"self": 0.0003639380000208803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015393199999493845,
"count": 10,
"is_parallel": true,
"self": 0.0015393199999493845
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.68275249400062,
"count": 18199,
"is_parallel": true,
"self": 10.142913369002144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.269304953002461,
"count": 18199,
"is_parallel": true,
"self": 5.269304953002461
},
"communicator.exchange": {
"total": 170.32562205599368,
"count": 18199,
"is_parallel": true,
"self": 170.32562205599368
},
"steps_from_proto": {
"total": 32.94491211600234,
"count": 18199,
"is_parallel": true,
"self": 6.076013930010788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.868898185991554,
"count": 181990,
"is_parallel": true,
"self": 26.868898185991554
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013588399997388478,
"count": 1,
"self": 0.00013588399997388478,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.5541181679928,
"count": 667517,
"is_parallel": true,
"self": 13.801305898991018,
"children": {
"process_trajectory": {
"total": 237.96886716300094,
"count": 667517,
"is_parallel": true,
"self": 237.32966138300094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6392057799999975,
"count": 4,
"is_parallel": true,
"self": 0.6392057799999975
}
}
},
"_update_policy": {
"total": 182.78394510600083,
"count": 90,
"is_parallel": true,
"self": 53.779919349999204,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.00402575600162,
"count": 4581,
"is_parallel": true,
"self": 129.00402575600162
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10605750100000932,
"count": 1,
"self": 0.0011978530000078536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10485964800000147,
"count": 1,
"self": 0.10485964800000147
}
}
}
}
}
}
}