Introduction
This is the repo for storing the reviewing note regarding several domains in reinforcement learning
basic_RL
- UCL course on RL led by David Silver
- "Reinforcement Learning An Introduction" by Richard S. Sutton and Andrew G. Barto
- Introduction to Reinforcement Learning with Function Approximation by R.Sutton, NIPS 2015
DRL(Deep RL)
MARL(Multi-Agent RL)
- Multiagent Reinforcement Learning by Daan Bloembergen, Daniel Hennes, Michael Kaisers, Peter Vrancx. ECML, 2013.
- Bus¸oniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multi-agent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics. Part C: Applications and Reviews 38(2), 156–172 (2008)
MORL(Multi-objective RL)
This topic is about RL algorithms dealing with the case where learning agent has to learn the preferences among the multiple goals in the environment
- Multiobjective Reinforcement Learning: A Comprehensive Overview by C.Liu et al., 2015
- A Multi-Objective Deep Reinforcement Learning Framework by TT.Nguyen, 2018
safe_reinforcement_learning
This topic is about RL algorithms aims the safe exploration during the early stage in learning process.
- A Comprehensive Survey on Safe Reinforcement Learning by Garcia and Fernandez, 2015
- Bayes Optimisation
- Tutorial on Safe Reinforcement Learning by Felix Berkenkamp, Andreas Krause
transfer_learning
This topic is about the algorithms aims at successfully transferring the knowledge from the source task to the target task to speed-up learning process.
- A Survey on Transfer Learning by Sinno Jialin Pan and Qiang Yang, 2011
- Transfer in Reinforcement Learning: a Framework and a Survey by Alessandro Lazaric, 2013
imitation_learning
Lectures
- CS 294-112 at UC Berkeley Deep Reinforcement Learning
- IMITATION LEARNING TUTORIAL at ICML 2018
- CMU 10703: Deep Reinforcement Learning and Control
- Imitation Learning for Robotics, Winter 2019, CSC2621