Jonathan Mugan and Benjamin Kuipers. 2008.
Continuous-domain reinforcement learning
using a learned qualitative state representation.
International Workshop on Qualitative Reasoning (QR-08).
We present a method that allows an agent to learn a qualitative state representation that can be applied to reinforcement learning. By exploring the environment the agent is able to learn an abstraction that consists of landmarks that break the space into qualitative regions, and rules that predict changes in qualitative state. For each predictive rule the agent learns a context consisting of qualitative variables that predicts when the rule will be successful. The regions of this context in which the rule is likely to succeed serve as a natural goals for reinforcement learning. The reinforcement learning problems created by the agent are simple because the learned abstraction provides a mapping from the continuous input and motor variables to discrete states that aligns with the dynamics of the environment.