pardee-wal's picture
First Push
1425602 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7316715121269226,
"min": 0.731191098690033,
"max": 2.866107225418091,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6953.80615234375,
"min": 6953.80615234375,
"max": 29257.22265625,
"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": 12.907366752624512,
"min": 0.28773796558380127,
"max": 12.96267318725586,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2516.9365234375,
"min": 55.821163177490234,
"max": 2647.547119140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07189483130986998,
"min": 0.06161195539655939,
"max": 0.07315469890069352,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28757932523947993,
"min": 0.25637654167047574,
"max": 0.360024282366366,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1857576925380557,
"min": 0.13750537388784556,
"max": 0.279679682617094,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7430307701522229,
"min": 0.5500214955513822,
"max": 1.3705402568859213,
"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": 25.727272727272727,
"min": 3.409090909090909,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 150.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.409090909090909,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 150.0,
"max": 1407.0,
"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": "1780643281",
"python_version": "3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0]",
"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": "1.2.0.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": "1780643740"
},
"total": 459.3452633139999,
"count": 1,
"self": 0.6470946819999881,
"children": {
"run_training.setup": {
"total": 0.026235702999997557,
"count": 1,
"self": 0.026235702999997557
},
"TrainerController.start_learning": {
"total": 458.6719329289999,
"count": 1,
"self": 0.36681508899278015,
"children": {
"TrainerController._reset_env": {
"total": 2.9481803370000534,
"count": 1,
"self": 2.9481803370000534
},
"TrainerController.advance": {
"total": 455.2755438870073,
"count": 18192,
"self": 0.37899775800133284,
"children": {
"env_step": {
"total": 333.0290406369969,
"count": 18192,
"self": 259.9357298669893,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.86808151699415,
"count": 18192,
"self": 1.2739828719995785,
"children": {
"TorchPolicy.evaluate": {
"total": 71.59409864499457,
"count": 18192,
"self": 71.59409864499457
}
}
},
"workers": {
"total": 0.22522925301348096,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.74067611100077,
"count": 18192,
"is_parallel": true,
"self": 228.18744383499313,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0048746539999910965,
"count": 1,
"is_parallel": true,
"self": 0.0034850570000344305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001389596999956666,
"count": 10,
"is_parallel": true,
"self": 0.001389596999956666
}
}
},
"UnityEnvironment.step": {
"total": 0.04963797199991404,
"count": 1,
"is_parallel": true,
"self": 0.0008447319999049796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042378199998438504,
"count": 1,
"is_parallel": true,
"self": 0.00042378199998438504
},
"communicator.exchange": {
"total": 0.04569496800002071,
"count": 1,
"is_parallel": true,
"self": 0.04569496800002071
},
"steps_from_proto": {
"total": 0.0026744900000039706,
"count": 1,
"is_parallel": true,
"self": 0.00048443199989378627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021900580001101844,
"count": 10,
"is_parallel": true,
"self": 0.0021900580001101844
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.55323227600763,
"count": 18191,
"is_parallel": true,
"self": 10.53962382999498,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.551151021002056,
"count": 18191,
"is_parallel": true,
"self": 5.551151021002056
},
"communicator.exchange": {
"total": 174.6915816620077,
"count": 18191,
"is_parallel": true,
"self": 174.6915816620077
},
"steps_from_proto": {
"total": 37.77087576300289,
"count": 18191,
"is_parallel": true,
"self": 6.761619945980897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.009255817021995,
"count": 181910,
"is_parallel": true,
"self": 31.009255817021995
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.86750549200906,
"count": 18192,
"self": 0.453048348997072,
"children": {
"process_trajectory": {
"total": 26.63010410801178,
"count": 18192,
"self": 26.234646383011864,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3954577249999147,
"count": 4,
"self": 0.3954577249999147
}
}
},
"_update_policy": {
"total": 94.78435303500021,
"count": 90,
"self": 38.216974725999194,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.567378309001015,
"count": 4587,
"self": 56.567378309001015
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0209998890786665e-06,
"count": 1,
"self": 1.0209998890786665e-06
},
"TrainerController._save_models": {
"total": 0.08139259499989748,
"count": 1,
"self": 0.0008136479998483992,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08057894700004908,
"count": 1,
"self": 0.08057894700004908
}
}
}
}
}
}
}