Deep Reinforcement Learning Hands-On

Things to try

In this chapter, we've only just started playing with MiniWoB, by touching upon the six easiest environments from the full set of 80 problems, so there is plenty of uncharted territory ahead. If you want to practice, there are several items you can experiment with:

• Testing the robustness of demonstrations to noisy clicks.
• Implementing training of the value head of A2C based on demonstration data.
• Implementing more sophisticated mouse control, like Move mouse N pixels left/right/top/bottom.
• Using some pretrained OCR net (or train your own!) to extract text information from the observations.
• Taking other problems and trying to solve them. There are some quite tricky and fun problems, like sort items using drag-n-drop, or repeat the pattern ...