Some of the most successful recent applications of reinforcement learning have used neural networks and the TD algorithm to learn evaluation functions. In this paper, we examine t...
Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-wor...
The ways in which an agent’s actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of ...
Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer...
Knowledge-based planning methods offer benefits over classical techniques, but they are time consuming and costly to construct. There has been research on learning plan knowledge ...
In this paper we present a genetic algorithm applied to the problem of mission planning for Joint Suppression of Enemy Air Defenses (JSEAD) in support of air strike operations. Th...