Learning Action Models
Papers from the AAAI Workshop
Wei-Min Shen, Program Chair
The goal of this workshop is to develop and communicate technologies that enable active learning systems, based on their own percepts and actions, to abstract a model from their environment and to incorporate that model into their actions, thereby improving their long-term performance.
Learning action models has been a fundamental problem in fields such as adaptive control and system identification. Recent progress in reinforcement learning and robot learning shows clearly that the learning of such models is a very important topic within the AI learning community as well. It affords an opportunity for high-level representations for reasoning about the environment to interact usefully with the low-level action model. The papers in this technical report attempt to surmount the gap between the high-level cognitive models and the robotic hardware.