Books & Papers

  • “Reinforcement Learning: An introduction,” Second edition, in progress, by Richard S. Sutton and Andrew G. book

  • “Algorithms for Reinforcement Learning,” by Csaba Szepesvari book

  • “Reinforcement Learning and Dynamic Programming Using Function Approximators by Busoniu,” Babuska, De Schutter and Ernst book

  • “Perspectives of Approximate Dynamic Programming,” W. B. Powell, Annals of Operations Research, Annals of Operations Research (2012), Springer. tutorial

  • “Convergence of Q-learning: a simple proof,” by Melo paper

  • “Deterministic Policy Gradient Algorithms,” by Silver, Lever, Heess, Degris, Wierstra, Riedmiller, 2014 paper appendices

Video Lectures


  • Berkeley's Deep Reinforcement Learning course CS 294 website including additional materials, presentations, video lectures

  • Course on Reinforcement Learning by Alessandro Lazaric from from the Electronic and Informatics Department of Politecnico di Milano website

  • Deep Reinforcement Learning and Control CMU 10703 website

  • Reinforcement Learning, Stanford, MS&E338, Benjamin Van Roy website

Optional paper for the project implementation

  • Continuous control with deep reinforcement learning Lillicrap a. al. paper

  • Benchmarking Deep Reinforcement Learning for Continuous Control Duan et al paper

RL enviourment test and code

  • OpenAI Gym: a toolkit for developing and comparing reinforcement learning algorithms link

  • TensorForce: Code and enviourment TensorForce