Reinforcement-based learning with automatic categorization
Josep M. Porta · DIGITAL.CSIC (Spanish National Research Council (CSIC)) · 1999
Abstract. In this work, we present a reinforcement-based learning algorithm that includes the automatic categorization of both sensors and actions. The categorization process is prior to any application of reinforcement learning. If categories are not at the adequate abstraction level, the problem could be not learnable. The categorization process is usually done by the programmer and is not considered as part of the learning process. However, in complex tasks, environments, or agents, this manual process could become extremely difficult. To solve this inconvenience, we propose to include the categorization into the learning process. We sketch an algorithm to automatically learn to achieve a task through reinforcement learning that works without needing a previous categorization process. First results of the application of this algorithm are shown. 1