You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

rein.rst 585 B

4 years ago
123456789101112131415161718192021222324252627282930313233
  1. API - Reinforcement Learning
  2. ==============================
  3. Reinforcement Learning.
  4. .. automodule:: tensorlayer.rein
  5. .. autosummary::
  6. discount_episode_rewards
  7. cross_entropy_reward_loss
  8. log_weight
  9. choice_action_by_probs
  10. Reward functions
  11. ---------------------
  12. .. autofunction:: discount_episode_rewards
  13. Cost functions
  14. ---------------------
  15. Weighted Cross Entropy
  16. ^^^^^^^^^^^^^^^^^^^^^^^^
  17. .. autofunction:: cross_entropy_reward_loss
  18. Log weight
  19. ^^^^^^^^^^^^^^
  20. .. autofunction:: log_weight
  21. Sampling functions
  22. ---------------------
  23. .. autofunction:: choice_action_by_probs

TensorLayer3.0 是一款兼容多种深度学习框架为计算后端的深度学习库。计划兼容TensorFlow, Pytorch, MindSpore, Paddle.