CS234: Reinforcement Learning
Stanford's course on reinforcement learning, covering Markov decision processes, model-free and model-based methods, value function approximation, policy gradients, and exploration, taught by Emma Brunskill.
Stanford CS234: Reinforcement Learning, Spring 2024, taught by Emma Brunskill. The course covers the formal frameworks and techniques for sequential decision making, including Markov decision processes, model-free and model-based reinforcement learning, value function approximation, policy gradient methods, and exploration, together with applications to robotics, healthcare, and education.
This is a curated third-party resource. All credit and citation belongs to Emma Brunskill and Stanford University.