HajNemat's picture
First Push
27efcd2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8810557723045349,
"min": 0.8810557723045349,
"max": 2.870035171508789,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8441.3955078125,
"min": 8441.3955078125,
"max": 29423.6015625,
"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": 13.095549583435059,
"min": 0.30395519733428955,
"max": 13.095549583435059,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2553.632080078125,
"min": 58.967308044433594,
"max": 2660.677734375,
"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": 0.07452873268173825,
"min": 0.05949391111532938,
"max": 0.07476008925039102,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.298114930726953,
"min": 0.25808783951352404,
"max": 0.3738004462519551,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18997737502350528,
"min": 0.12450359638451652,
"max": 0.3048259574262535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7599095000940211,
"min": 0.4980143855380661,
"max": 1.339430707634664,
"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": 25.818181818181817,
"min": 3.4318181818181817,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 151.0,
"max": 1411.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.4318181818181817,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 151.0,
"max": 1411.0,
"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": "1726679644",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726680372"
},
"total": 727.624427659,
"count": 1,
"self": 0.7438645110001971,
"children": {
"run_training.setup": {
"total": 0.08066200499990828,
"count": 1,
"self": 0.08066200499990828
},
"TrainerController.start_learning": {
"total": 726.7999011429999,
"count": 1,
"self": 1.188077664009711,
"children": {
"TrainerController._reset_env": {
"total": 3.8760010270000294,
"count": 1,
"self": 3.8760010270000294
},
"TrainerController.advance": {
"total": 721.6302098399902,
"count": 18205,
"self": 0.5634561609703042,
"children": {
"env_step": {
"total": 721.0667536790199,
"count": 18205,
"self": 548.2574743040008,
"children": {
"SubprocessEnvManager._take_step": {
"total": 172.29817412100442,
"count": 18205,
"self": 3.4911221200096634,
"children": {
"TorchPolicy.evaluate": {
"total": 168.80705200099476,
"count": 18205,
"self": 168.80705200099476
}
}
},
"workers": {
"total": 0.5111052540147512,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 724.1277150240052,
"count": 18205,
"is_parallel": true,
"self": 342.4113005560273,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031105130000241843,
"count": 1,
"is_parallel": true,
"self": 0.0009236069998905805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002186906000133604,
"count": 10,
"is_parallel": true,
"self": 0.002186906000133604
}
}
},
"UnityEnvironment.step": {
"total": 0.10862708699994528,
"count": 1,
"is_parallel": true,
"self": 0.0011467969999330307,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000579773000026762,
"count": 1,
"is_parallel": true,
"self": 0.000579773000026762
},
"communicator.exchange": {
"total": 0.10392106599999806,
"count": 1,
"is_parallel": true,
"self": 0.10392106599999806
},
"steps_from_proto": {
"total": 0.002979450999987421,
"count": 1,
"is_parallel": true,
"self": 0.0005662970000912537,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002413153999896167,
"count": 10,
"is_parallel": true,
"self": 0.002413153999896167
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 381.71641446797787,
"count": 18204,
"is_parallel": true,
"self": 18.38082995198795,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.909883662999619,
"count": 18204,
"is_parallel": true,
"self": 8.909883662999619
},
"communicator.exchange": {
"total": 302.1290647479981,
"count": 18204,
"is_parallel": true,
"self": 302.1290647479981
},
"steps_from_proto": {
"total": 52.29663610499222,
"count": 18204,
"is_parallel": true,
"self": 11.118470420979975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.17816568401224,
"count": 182040,
"is_parallel": true,
"self": 41.17816568401224
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00025970799993046967,
"count": 1,
"self": 0.00025970799993046967,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 712.6250990330074,
"count": 910975,
"is_parallel": true,
"self": 23.889349791078757,
"children": {
"process_trajectory": {
"total": 393.01045276792956,
"count": 910975,
"is_parallel": true,
"self": 391.7656603849297,
"children": {
"RLTrainer._checkpoint": {
"total": 1.24479238299989,
"count": 4,
"is_parallel": true,
"self": 1.24479238299989
}
}
},
"_update_policy": {
"total": 295.72529647399904,
"count": 90,
"is_parallel": true,
"self": 76.60512941700006,
"children": {
"TorchPPOOptimizer.update": {
"total": 219.12016705699898,
"count": 4584,
"is_parallel": true,
"self": 219.12016705699898
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1053529040000285,
"count": 1,
"self": 0.0018106089999037067,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1035422950001248,
"count": 1,
"self": 0.1035422950001248
}
}
}
}
}
}
}