Upgrade to Pro — share decks privately, control downloads, hide ads and more …

DeepRacer for learning RL

DeepRacer for learning RL

2019.4.6 Developers.IO at OKAYAMA.

貞松政史

April 06, 2019
Tweet

More Decks by 貞松政史

Other Decks in Technology

Transcript

  1. & .-*  (2  ,0'/4"# 51  83;7 +)

    !&%$9( 6:  Attention
  2. 4 os t m ( L @S g E b

    i _d L rMI D @ E ( ( ( ) ( e a n k AWS E
  3. 14 DeepRacer 1/18       

     3D  AWS DeepRacer League
  4. 18 AWS DeepRacer League ⁻ 0 1 : 9 A

    ⁻ 9 2 R ⁻   ⁻ D I ⁻ 1 2 ⁻   https://aws.amazon.com/jp/deepracer/league/
  5. 20   (Artificial Intelligence, AI)  (Machine Learning, ML)

        NeuralNetwork DeepLearning   
  6. 24 DeepRacer     Cliped PPO PPO (Proximal

    Policy Optimization) OpenAI2017 
  7. 42 SageMaker “RL”  ⁻ ⁻ M ⁻ M M

    ⁻ M   ⁻ ⁻ ⁻ J M S
  8. 44 SageMaker        

      https://dev.classmethod.jp/machine -learning/sagemaker-robomaker- deepracer-sample/
  9. 45      $#   "

        ! https://github.com/awslabs/amazon-sagemaker-examples
  10. 53    Best Practices when training with PPO

    (Unity Technologies) https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-PPO.md        
  11. 54 DeepRacer "%    !   "%

            $#     !   !
  12. 61 • g • + + • M D c

    • R S D a k • b • LL e