10 – Summary

I hope you got a good sense of deep Q learning, how it combines the best of reinforcement learning with recent advances in deep learning. I also hope that you’ll realize how this opens up a world of possibilities for you to experiment with different neural net architectures value functions, learning algorithms and not to mention the wide variety of environments you can tackle. Before you move on to studying other reinforcement learning approaches, I encourage you to try and implement agents for different problems especially on platforms like OpenAI Gym. See which ones deep Q learning is able to solve reliably, and which ones it finds challenging. That will help you gain a deeper understanding of the algorithm and motivate the need for other approaches such as policy gradients and actor-critic methods.

%d 블로거가 이것을 좋아합니다: