| 1957 | Bellman | Dynamic Programming | 2장 기호와 퍼셉트론 1956–74 |
| 1959 | Samuel | Some Studies in Machine Learning Using the Game of Checkers | 2장 기호와 퍼셉트론 1956–74 |
| 1983 | Barto et al. | Neuronlike adaptive elements that can solve difficult learning control problems | 3장 지식 시스템과 연결주의 1974–93 |
| 1988 | Sutton | Learning to predict by the methods of temporal differences | 3장 지식 시스템과 연결주의 1974–93 |
| 1989 | Watkins | Learning from Delayed Rewards | 3장 지식 시스템과 연결주의 1974–93 |
| 1992 | Watkins & Dayan | Q-learning | 4장 통계 학습 1990–2011 |
| 1992 | Williams | Simple statistical gradient-following algorithms for connectionist reinforcement learning | 4장 통계 학습 1990–2011 |
| 1995 | Tesauro | Temporal difference learning and TD-Gammon | 4장 통계 학습 1990–2011 |
| 1998 | Kaelbling et al. | Planning and acting in partially observable stochastic domains | 4장 통계 학습 1990–2011 |
| 1998 | Sutton & Barto | Reinforcement Learning: An Introduction | 4장 통계 학습 1990–2011 |
| 1999 | Sutton et al. | Policy Gradient Methods for Reinforcement Learning with Function Approximation | 4장 통계 학습 1990–2011 |
| 2013 | Mnih et al. | Playing Atari with Deep Reinforcement Learning | 5장 딥러닝 2012–17 |
| 2015 | Mnih et al. | Human-level control through deep reinforcement learning | 5장 딥러닝 2012–17 |
| 2015 | Schulman et al. | Trust Region Policy Optimization | 5장 딥러닝 2012–17 |
| 2015 | Lillicrap et al. | Continuous control with deep reinforcement learning | 5장 딥러닝 2012–17 |
| 2016 | Silver et al. | Mastering the game of Go with deep neural networks and tree search | 5장 딥러닝 2012–17 |
| 2016 | Mnih et al. | Asynchronous Methods for Deep Reinforcement Learning | 5장 딥러닝 2012–17 |
| 2017 | Schulman et al. | Proximal Policy Optimization Algorithms | 5장 딥러닝 2012–17 |
| 2017 | Silver et al. | Mastering the game of Go without human knowledge | 5장 딥러닝 2012–17 |
| 2018 | Silver et al. | A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play | 6장 사전학습·생성 2017–22 |
| 2019 | Schrittwieser et al. | Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model | 6장 사전학습·생성 2017–22 |