This paper introduces a novel approach for abstraction selec- tion in reinforcement learning problems modelled as factored. Markov decision processes (MDPs), ...

Aug 6, 2013 · This article addresses reinforcement learning problems based on factored Markov decision processes (MDPs) in which the agent must choose ...

This article addresses reinforcement learning problems based on factored Markov decision processes (MDPs) in which the agent must choose among a...

PDF | This paper introduces a novel approach for abstraction selec-tion in reinforcement learning problems modelled as factored Markov decision.

This paper introduces a novel approach for abstraction selection in reinforcement learning problems modelled as factored Markov decision processes (MDPs), ...

Jul 4, 2013 · This paper introduces a novel approach for abstraction selection in reinforcement learning problems modelled as factored Markov decision ...

We show empirically that it can consistently select an appro- priate abstraction using very little sample data, and that it significantly improves skill ...

This article addresses reinforcement learning problems based on factored Markov decision processes (MDPs) in which the agent must choose among a set of ...

Our analysis shows that a carefully designed hypothesis test can balance this finite-sample tradeoff even when none of the abstractions are perfect, and works ...

Successful reinforcement learning requires large amounts of data, compute, and some luck. We explore the ability of abstraction(s) to reduce these ...