We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
A long-standing challenge in interactive entertainment is the creation of story-based games with dynamically responsive story-lines. Such games are populated by multiple objects a...
Mark J. Nelson, David L. Roberts, Charles Lee Isbe...
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Using a distributed algorithm rather than a centralized one can be extremely beneficial in large search problems. In addition, the incorporation of machine learning techniques lik...
Abstract— Groups of reinforcement learning agents interacting in a common environment often fail to learn optimal behaviors. Poor performance is particularly common in environmen...