Reinforcement Learning Paper Review and Learning Resource

This repo contains RL paper reviews and RL leanrning resources

Reinforcement Learning (RL) has become increasingly pivotal in the advancement of Generative AI, enabling models to learn and adapt through interactions with their environment. To support your journey in mastering RL, I've curated a list of top-tier learning resources and papers on the interesting branches of RL (e.g., Causal RL, Model-based RL, etc):

1. Hugging Face's Deep RL Course: A free, open-source course that guides learners from beginner to expert in deep reinforcement learning https://lnkd.in/gd3985YQ

2. OpenAI Spinning Up: An educational resource that provides a comprehensive introduction to RL concepts and algorithms. https://lnkd.in/ggi7Z7Xh

3. Coursera: RL Specialization - Offered by the University of Alberta, this specialization comprises four courses that delve into the fundamentals and applications of RL. Learners will explore adaptive learning systems and implement complete RL solutions https://lnkd.in/ghgeAeS8

4. Deepmind x UCL RL Course: A series of lectures by a leading expert in the field, covering foundational to advanced RL topics. YouTube playlist) https://lnkd.in/gw8re-er Github) https://lnkd.in/g7rH6yms

5. Stanford Online: CS234 - Reinforcement Learning Stanford's CS234 course provides a comprehensive introduction to RL, covering core challenges and approaches, including generalization and exploration. The curriculum combines lectures with practical assignments to solidify understanding. https://lnkd.in/gUzUvRns

6. Stanford Online: CS224R - Deep Reinforcement Learning Focusing on algorithms that combine deep learning with RL, this course emphasizes practical methods for learning behavior from experience. It's particularly relevant for applications in robotics and control systems. https://lnkd.in/gmb6npfp

7. UC Berkeley's CS 285: Deep RL. Focusing on algorithms that combine deep learning with RL https://lnkd.in/gGbM8E8u

8. UC Berkeley Artificial Intelligence Research Lab (BAIR): Model-based RL https://bair.berkeley.edu/blog/2019/12/12/mbpo/ https://bair.berkeley.edu/blog/2017/11/30/model-based-rl/

9. Causal Reinforcement Learning (ICML 2020 Tutorial) https://crl.causalai.net/ A Survey on Causal Reinforcement Learning https://arxiv.org/abs/2302.05209

10. Inverse RL and Dynamic Discrete Choice Model An Empirical Risk Minimization Approach for Offline Inverse RL and Dynamic Discrete Choice Model https://arxiv.org/abs/2502.14131

11. Active Learning - Prices and Promotions https://faculty.washington.edu/hemay/Pricing_Slides.pdf

12. Decision Transformer https://github.com/kzl/decision-transformer