Reading

Papers and Books

1. Sutton, Barto, Reinforcement Learning an Introduction. (classic textbook)
2. White, Real applications of markov decision processes
3. Kober, Bagnell, Peters, Reinforcement learning in robotics: a survey, 2013

Policy gradient

1. Williams, Simple statistical gradient-following algorithms for connectionist reinforcement learning, 1992
2. Sutton et al. Policy gradient methods for reinforcement learning with function approximation, 2000
3. Kakade, A natural policy gradient, 2001**
4. Kakade, Langford, Approximately optimal approximate reinforcement learning, 2002
5. Schulman et al. Trust region policy optimization, 2015**
6. Schulman et al. High-dimensional continuous control using generalized advantage estimation, 2016
7. Rajeswaran et al. Towards generalization and simplicity in continuous control, 2017**
8. Schulman et al. Proximal Policy Optimization Algorithms, 2017
9. Mnih et al. Asynchronous Methods for Deep Reinforcement Learning, 2016
10. Toussaint, Gradient descent lecture notes, 2012**

MCTS

1. A Survey of MCTS Methods
2. Bandit Based Monte-Carlo Planning

Related Courses

1. DeepRL course at UC Berkeley, Fall 2017
2. DeepRL course at CMU, Spring 2017
3. Intelligent Control course at UW, Spring 2015
4. RL course at Stanford, Winter 2017
5. RL course at IIT Madras, Fall 2016
6. RL course at UCL, 2015