How to handle invalid/illegal actions/moves in Reinforcement Learning toolbox?

7 次查看（过去 30 天）
Lymperis Perakis
Lymperis Perakis 2019-8-8
回答： Rajani Mishra 2019-8-21
I have implemented a Reinforcement Learning Algorithm, where some actions are not legal/valid depending on the state. What is the best way to deal with this problem? I have tried to give negative rewards and stop the episode if an illegal action is selected, but it does not seem to work. I also tried to just ignore these actions, but then the agent keeps making the same move until it reaches the max episodes during the training. My best approach was to make the next possible action, instead of the selected one and although it has better results than the other options, it does not seem to be a good way to deal with it. I have read on the AlphaGo paper that "Illegal moves are masked out by setting their probabilities to zero, and re-normalising the probabilities for remaining moves." Is there a way to implement this on Matlab and if not what would be the best way to avoid the invalid moves ?

请先登录，再回答此问题。

回答（1 个）

Rajani Mishra
Rajani Mishra 2019-8-21
To implement your own custom reinforcement learning algorithms, you can create a custom agent.
Specify properties of the agent for creating and training the agent. Refer this link for creating custom agents : https://www.mathworks.com/help/reinforcement-learning/ug/custom-agents.html
I found one example of a Reinforcement learning agent, link for which is:https://www.mathworks.com/help/reinforcement-learning/ug/train-q-learning-agent-to-solve-basic-grid-world.html

类别

在 Help Center 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

标签

产品


版本

R2019a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by