강화학습 이론 정리 (2022.03~2022.07)
It is possible to learn reinforcement learning fundamentals that directly analyze reinforcement learning algorithms.
- Textbook Review: Reinforcement Learning: An Introduction, 2nd edition
- Ch 2: Multi-arm Bandit by Woojin Park
- Ch 3: Finite Markov Decision Process by Dido Choi
- Ch 4: Dynamic Programming by Sunwoong Choi
- Ch 5: Monte Carlo Methods by Yoongeun Kwon
- Ch 6: Temporal Difference Learning by Younghwa Oh
- Ch 7: N-step Bootstrapping by Yubin Kim
- Ch 8: Planning and Learning with Tabular Methods by Jaeshik Shin
- Ch 9: On-policy Prediction with Approximation by Jaeshik Shin
- Ch 10: On-policy Control with Approximation by Dido Choi
- Ch 11: Off-policy Methods with Approximation by Younghwa Oh
- Ch 12: Eligibility Traces by Yoongeun Kwon
[1] R.S. Sutton and A.G. Barto, “Reinforcement Learning: An Introduction 2nd Edition”, The MIT Press, Cambridge, 2018.