Awesome

reinforcement-learning

To finish my thesis, "Methods and implementations for coordinated multi-agent learning", which involves a research on RL from single agent to multi-agent, as well as the state-of-the-art in collaborative and coordinated multi-agent learning algorithms and implementations, the implementations in MATLAB for some RL methods are done. The thesis paper is also uploaded, where contains the references.

Single Agent Reinforcement Learning

• Dynamic Programming
• Monte Carlo Methods
• Temporal-Difference Learning
• Linear Function Approximation
• Deep-Q Network
• Policy Gradient with Linear Function Approximation

Multi-Agent Reinforcement Learning

• Centralized Q-Learning
• Hysteretic Q-Learning
• Multi-Agent Actor-Critic