Key Papers

Deep Learning Theory: https://stats385.github.io/readings, FAST.AI (practical)

Reinforcement Basics:

• Richard Sutton Book

• Emma and stanford COurse:

• David Silver Course: course

Classic Papers:

• MDPs: Bellman 1957

• TD-Learning: Sutton 1988

• Q-Learning: Watkins and Dayan 1992

• REINFORCE: Williams 1992

• Prioritized Sweeping: Moore and Atkeson 1993

• Markov Games and RL: Littman 1994

• Value function approximation: Boyan and Moore 1995

• Complexity of MDPs: Littman, Dean, Kaelbling 1995

• RL for Backgammon: Tesauro 1995

• POMDPs: Kaelbling, Littman, Cassandra 1998

• Reward Shaping: Ng, Harada, and Russell 1999

• Policy Gradients: Sutton, McAllaster, Singh, Mansour 2000

• Options/Temporal Abstractions: Sutton, Precup, Singh

• Hierarchical RL: Dietterich 2000

• Model-based RL with guarantees #1: Kearns and Singh 2002

• Model-based RL with guarantees #2: Braffman and Tennenholtz 2002

• Inverse RL: Abbeil and Ng 2004

Deep RL:

Deep RL David Silver Tutorial: watch NIPS keynote and DRL tutorial and Survey Papers:

1. DEEP REINFORCEMENT LEARNING: AN OVERVIEW,

2. https://arxiv.org/pdf/1708.05866.pdf

3. A long peek into RL

4. Principles of deep RL:

5. Critique: https://www.alexirpan.com/2018/02/14/rl-hard.html