Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
A major paradigm of modeling the decision making of autonomous agents is through behavior-based network models. The network consists of distributed behaviors that compete (or coop...
We examine the so-called rigorous support vector machine (RSVM) approach proposed by Vapnik (1998). The formulation of RSVM is derived by explicitly implementing the structural ris...
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, r...
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...