Q-learning (Watkins, 1989) is a simple way for agents to learn how to act optimally in controlled Markovian domains. It amounts to an incremental method for dynamic programming which imposes limited computational demands. It works by successively improving its evaluations of the quality of particular actions at particular states. This paper presents and proves in detail a convergence theorem for Q,-learning based on that outlined in Watkins (1989). We show that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action-values are represented discretely. We also sketch extensions to the cases of non-discounted, but absorbing, Markov environments, and where many Q values can be changed each iteration, rather than just one.

WindyGridWorldQLearning.m

• We are an exchange download platform that only provides communication channels. The downloaded content comes from the internet. Except for download issues, please Google on your own.
• The downloaded content is provided for members to upload. If it unintentionally infringes on your copyright, please contact us.
• Please use Winrar for decompression tools
• If download fail, Try it againg or Feedback to us.
• If downloaded content did not match the introduction, Feedback to us，Confirm and will be refund.
• Before downloading, you can inquire through the uploaded person information

Nothing．