Reinforcement Learning and Geometric Algorithms
CMPS 499/CSCE 572
Miao Jin Office hours: TR 9:30am - 11:00am ACTR 237
Times & Places
TR 11:00am - 12:15pm, ACTR 113
Reinforcement Learning: a range of topics related to reinforcement learning.
Geometric Algorithms: a range of topics related to geometric representation
and computation. We will study fundamental data structures and algorithms from computational geometry and their applications to problems that occur in practice.
- Markov decision processes
- Dynamic programming
- Monte Carlo learning
- Temporal difference learning
- Value function approximation
- Policy gradient
- Integration of learning and planning
Topics may include:
- Convex hulls
- Line segment intersection
- Triangulating a polygon
- Enclosing circle
- Voronoi diagrams
- Delaunay Triangulations
- Robot Motion Planning
CMPS 341 Formal Foundations of Computer Science.
An Introduction to Reinforcement Learning, Second edition, in progress (Available free online! ) by Richard S. Sutton and Andrew G. Barto (optional).
Computational Geometry, Algorithms and Applications by Mark de Berg et al
- 50% Reinforcement Learning Project
- 25% Midterm exam (Reinforcement Learning)
- 25% Final exam (Geometric Algorithms)