RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
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 ...
Hanna M. Pasula, Luke S. Zettlemoyer, Leslie Pack ...
Enforced hill-climbing is an effective deterministic hillclimbing technique that deals with local optima using breadth-first search (a process called "basin flooding"). ...
Peer-to-peer distributed virtual environments (DVE's) distribute state tracking and state transitions. Many DVE's - such as online games - require ways to fairly determi...
While much work on learning in planning focused on learning domain physics (i.e., action models), and search control knowledge, little attention has been paid towards learning use...
Nan Li, William Cushing, Subbarao Kambhampati, Sun...