Tips on Reinforcement Learning

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement! ** Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Reinforcement Learning algorithms — an intuitive overview has a good overview of different approaches to RL. **

Courses & Tutorials¶

http://rail.eecs.berkeley.edu/deeprlcourse/

https://towardsdatascience.com/reinforcement-learning-q-learning-with-decision-trees-ecb1215d9131

Frameworks¶

The article A Comparison of Reinforcement Learning Frameworks: Dopamine, RLLib, Keras-RL, Coach, TRFL, Tensorforce, Coach and more has a comprehensive comparison of diferent reinforcement learning frameworks. Based on the author’s opinion, OpenAI Gym and Apache Ray RLLib are the best 2 libraries.

On Choosing a Deep Reinforcement Learning Library recommends Stable Baselines and TF-Agents.

https://github.com/kngwyu/rogue-gym

References¶

https://winderresearch.com/a-comparison-of-reinforcement-learning-frameworks-dopamine-rllib-keras-rl-coach-trfl-tensorforce-coach-and-more/

https://towardsdatascience.com/introduction-to-various-reinforcement-learning-algorithms-part-ii-trpo-ppo-87f2c5919bb9

https://arxiv.org/pdf/1707.06347.pdf

https://medium.com/jonathan_hui/rl-proximal-policy-optimization-ppo-explained-77f014ec3f12

https://openai.com/blog/openai-baselines-ppo/