Reinforcement Learning with Analogical Similarity to Guide Schema Induction and Attention
This work addresses the challenge of improving abstract reasoning and transfer in AI systems, though it appears incremental in combining existing theories.
The paper tackled the problem of enhancing reinforcement learning by integrating analogical reasoning to guide schema induction and attention, resulting in a computational synergy that was supported by simulation results.
Research in analogical reasoning suggests that higher-order cognitive functions such as abstract reasoning, far transfer, and creativity are founded on recognizing structural similarities among relational systems. Here we integrate theories of analogy with the computational framework of reinforcement learning (RL). We propose a psychology theory that is a computational synergy between analogy and RL, in which analogical comparison provides the RL learning algorithm with a measure of relational similarity, and RL provides feedback signals that can drive analogical learning. Simulation results support the power of this approach.