MrOceanMan's picture
First Push
c1a6082 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9323368668556213,
"min": 0.9237992763519287,
"max": 2.8380842208862305,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8860.9296875,
"min": 8860.9296875,
"max": 28971.1640625,
"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": 13.065634727478027,
"min": 0.35353541374206543,
"max": 13.065634727478027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2547.798828125,
"min": 68.58586883544922,
"max": 2646.91796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06578322831617198,
"min": 0.0633181875148747,
"max": 0.07483962891605116,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2631329132646879,
"min": 0.26099942307973834,
"max": 0.3741981445802558,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21637535672269617,
"min": 0.124043096828174,
"max": 0.28637104386500284,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8655014268907847,
"min": 0.496172387312696,
"max": 1.4231874852203854,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.65909090909091,
"min": 3.659090909090909,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 161.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.659090909090909,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 161.0,
"max": 1428.0,
"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": "1758659110",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758659550"
},
"total": 439.6780834540001,
"count": 1,
"self": 0.4284423430001425,
"children": {
"run_training.setup": {
"total": 0.030718216999957804,
"count": 1,
"self": 0.030718216999957804
},
"TrainerController.start_learning": {
"total": 439.218922894,
"count": 1,
"self": 0.34413215099073113,
"children": {
"TrainerController._reset_env": {
"total": 2.9867608149999114,
"count": 1,
"self": 2.9867608149999114
},
"TrainerController.advance": {
"total": 435.81092086700926,
"count": 18192,
"self": 0.360046108021038,
"children": {
"env_step": {
"total": 317.34837530699883,
"count": 18192,
"self": 249.04904489498335,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.07954976000235,
"count": 18192,
"self": 1.2335339229990723,
"children": {
"TorchPolicy.evaluate": {
"total": 66.84601583700328,
"count": 18192,
"self": 66.84601583700328
}
}
},
"workers": {
"total": 0.21978065201312802,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.37943037799903,
"count": 18192,
"is_parallel": true,
"self": 218.4917719330041,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005392319999941719,
"count": 1,
"is_parallel": true,
"self": 0.003952068999979019,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014402509999627,
"count": 10,
"is_parallel": true,
"self": 0.0014402509999627
}
}
},
"UnityEnvironment.step": {
"total": 0.08100875000002361,
"count": 1,
"is_parallel": true,
"self": 0.0005317310001373698,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003967220000049565,
"count": 1,
"is_parallel": true,
"self": 0.0003967220000049565
},
"communicator.exchange": {
"total": 0.07628101399996012,
"count": 1,
"is_parallel": true,
"self": 0.07628101399996012
},
"steps_from_proto": {
"total": 0.003799282999921161,
"count": 1,
"is_parallel": true,
"self": 0.0023900949997823773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014091880001387835,
"count": 10,
"is_parallel": true,
"self": 0.0014091880001387835
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.88765844499494,
"count": 18191,
"is_parallel": true,
"self": 10.311951509010669,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.492065679000348,
"count": 18191,
"is_parallel": true,
"self": 5.492065679000348
},
"communicator.exchange": {
"total": 166.24621522499558,
"count": 18191,
"is_parallel": true,
"self": 166.24621522499558
},
"steps_from_proto": {
"total": 36.83742603198834,
"count": 18191,
"is_parallel": true,
"self": 6.578537516026813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.25888851596153,
"count": 181910,
"is_parallel": true,
"self": 30.25888851596153
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.10249945198939,
"count": 18192,
"self": 0.4371815709768043,
"children": {
"process_trajectory": {
"total": 26.871253699012073,
"count": 18192,
"self": 26.47212938901214,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39912430999993376,
"count": 4,
"self": 0.39912430999993376
}
}
},
"_update_policy": {
"total": 90.79406418200051,
"count": 90,
"self": 37.71116651399882,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.08289766800169,
"count": 4587,
"self": 53.08289766800169
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.044000100591802e-06,
"count": 1,
"self": 1.044000100591802e-06
},
"TrainerController._save_models": {
"total": 0.07710801700000047,
"count": 1,
"self": 0.0008058650000748457,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07630215199992563,
"count": 1,
"self": 0.07630215199992563
}
}
}
}
}
}
}