rlanday's picture
First Push
a5fcb88
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8673873543739319,
"min": 0.8673873543739319,
"max": 2.868279218673706,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8310.4384765625,
"min": 8310.4384765625,
"max": 29437.150390625,
"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": 12.841236114501953,
"min": 0.3338128328323364,
"max": 12.841236114501953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.041015625,
"min": 64.75968933105469,
"max": 2586.7265625,
"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": 0.07331269585747756,
"min": 0.06098916515326767,
"max": 0.07736144779768188,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29325078342991023,
"min": 0.2500112664232552,
"max": 0.3804691520122373,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1939388528904494,
"min": 0.14383463190147178,
"max": 0.26186207221711383,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7757554115617976,
"min": 0.5753385276058871,
"max": 1.3033160275103999,
"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": 25.454545454545453,
"min": 4.0227272727272725,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 177.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 4.0227272727272725,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 177.0,
"max": 1398.0,
"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": "1685942334",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685942752"
},
"total": 418.0969735839999,
"count": 1,
"self": 0.32718156799978715,
"children": {
"run_training.setup": {
"total": 0.04409926700009237,
"count": 1,
"self": 0.04409926700009237
},
"TrainerController.start_learning": {
"total": 417.725692749,
"count": 1,
"self": 0.6001633879952806,
"children": {
"TrainerController._reset_env": {
"total": 4.165904509000029,
"count": 1,
"self": 4.165904509000029
},
"TrainerController.advance": {
"total": 412.8160317760048,
"count": 18205,
"self": 0.28813469599890595,
"children": {
"env_step": {
"total": 412.5278970800059,
"count": 18205,
"self": 296.63466850996974,
"children": {
"SubprocessEnvManager._take_step": {
"total": 115.61543369700075,
"count": 18205,
"self": 1.6779444469750615,
"children": {
"TorchPolicy.evaluate": {
"total": 113.93748925002569,
"count": 18205,
"self": 113.93748925002569
}
}
},
"workers": {
"total": 0.2777948730354183,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.8157618869984,
"count": 18205,
"is_parallel": true,
"self": 208.44964039000388,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00589358699994591,
"count": 1,
"is_parallel": true,
"self": 0.0041940969999814115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016994899999644986,
"count": 10,
"is_parallel": true,
"self": 0.0016994899999644986
}
}
},
"UnityEnvironment.step": {
"total": 0.04151357499995356,
"count": 1,
"is_parallel": true,
"self": 0.0006831340001554054,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005049349999808328,
"count": 1,
"is_parallel": true,
"self": 0.0005049349999808328
},
"communicator.exchange": {
"total": 0.03800000100000034,
"count": 1,
"is_parallel": true,
"self": 0.03800000100000034
},
"steps_from_proto": {
"total": 0.0023255049998169852,
"count": 1,
"is_parallel": true,
"self": 0.00039374600009978167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019317589997172036,
"count": 10,
"is_parallel": true,
"self": 0.0019317589997172036
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.36612149699454,
"count": 18204,
"is_parallel": true,
"self": 10.00447277802914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.157404416979944,
"count": 18204,
"is_parallel": true,
"self": 5.157404416979944
},
"communicator.exchange": {
"total": 161.84093021400417,
"count": 18204,
"is_parallel": true,
"self": 161.84093021400417
},
"steps_from_proto": {
"total": 31.36331408798128,
"count": 18204,
"is_parallel": true,
"self": 5.682382042974041,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.68093204500724,
"count": 182040,
"is_parallel": true,
"self": 25.68093204500724
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014286199984780978,
"count": 1,
"self": 0.00014286199984780978,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 411.3197048699467,
"count": 238071,
"is_parallel": true,
"self": 5.254198373930194,
"children": {
"process_trajectory": {
"total": 227.95643080701802,
"count": 238071,
"is_parallel": true,
"self": 227.11200229601764,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8444285110003875,
"count": 4,
"is_parallel": true,
"self": 0.8444285110003875
}
}
},
"_update_policy": {
"total": 178.10907568899847,
"count": 90,
"is_parallel": true,
"self": 47.247362477988645,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.86171321100983,
"count": 4587,
"is_parallel": true,
"self": 130.86171321100983
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14345021400004043,
"count": 1,
"self": 0.0009232539998720313,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1425269600001684,
"count": 1,
"self": 0.1425269600001684
}
}
}
}
}
}
}