Modeling Agents with Probabilistic Programs
Owain Evans, Andreas Stuhlmüller, John Salvatier, and Daniel Filan
This book describes and implements models of rational agents for (PO)MDPs and Reinforcement Learning. One motivation is to create richer models of human planning, which capture human biases and bounded rationality.
The book assumes basic programming experience but is otherwise self-contained. It includes short introductions to “planning as inference”, MDPs, POMDPs, inverse reinforcement learning, hyperbolic discounting, myopic planning, and multi-agent planning.