Effective and efficient forgetting of learned knowledge in Soar’s working and procedural memories

Effective management of learned knowledge is a challenge when modeling human-level behavior within complex, temporally extended tasks. This work evaluates one approach to this problem: forgetting knowledge that is not in active use (as determined by base-level activation) and can likely be reconstructed if it becomes relevant. We apply this model to the working and procedural memories of Soar. When evaluated in simulated, robotic exploration and a competitive, multi-player game, these policies improve model reactivity and scaling while maintaining reasoning competence. To support these policies for real-time modeling, we also present and evaluate a novel algorithm to efficiently forget items from large memory stores while preserving base-level fidelity.