ORCS E4529
Reinforcement Learning
Markov Decision Processes (MDP) and Reinforcement Learning (RL) problems. Reinforcement Learning algorithms including Q-learning, policy gradient methods, actor-critic method. Reinforcement learning while doing exploration-exploitation dilemma, multi-armed bandit problem. Monte Carlo Tree Search methods, Distributional, Multi-agent, and Causal Reinforcement Learning
Prerequisites & course information
Prerequisites: Probability and statistics, basic optimization e.g., familiarity with linear and convex optimization, gradient descent, basic algorithm design constructs, familiarity with programming in python.
Sources
- Course catalogue ↗2026-2027
- Catalogue entry ↗
Catalogue variants
- Reinforcement Learning · 3.00 points · University catalogue