Relativized options combine model minimization methods and a hierarchical reinforcement learning framework to derive compact reduced representations of a related family of tasks. ...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Abstract-- In this paper we investigate the effects of individual learning on an evolving population of situated agents. We work with a novel type of system where agents can decide...
Modular model is a particular type of committee machine and is comprised of a set of specialized (local) models each of which is responsible for a particular region of the input s...
This paper explores hybrid agents that use a variety of techniques to improve their performance in an environment over time. We considered, specifically, geneticlearning-parentin...