Learning Symbolic Models of Stochastic Domains

In this article, we work towards the goal of developing agents that can learn to act in complex worlds. We develop a a new probabilistic planning rule representation to compactly model model noisy, nondeterministic action effects and show how these rules can be effectively learned. Through experiments in simple planning domains and a 3D simulated blocks world with realistic physics, we demonstrate that this learning algorithm allows agents to effectively model world dynamics.

• Type: Journal
• Year: 2007
• Where: JAIR
• Authors: Hanna M. Pasula, Luke S. Zettlemoyer, Leslie Pack Kaelbling
• Keywords: JAIR 2007, Model, Probabilistic Planning Rule, Simple Planning Domains