Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture
This addresses the challenge of enabling AI systems to learn transferable, domain-independent strategies, which is incremental in applying memory-augmented networks to symbolic planning.
The authors tackled the problem of learning abstract strategies that transfer to unfamiliar tasks by developing a novel neural architecture inspired by computer designs, which learns algorithmic solutions via Evolution Strategies. They demonstrated strong generalization and abstraction on Sokoban, sliding block puzzles, and robotic manipulation tasks, scaling to arbitrary configurations and complexities.
A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems. Therefore, we present a novel architecture, based on memory-augmented networks, that is inspired by the von Neumann and Harvard architectures of modern computers. This architecture enables the learning of abstract algorithmic solutions via Evolution Strategies in a reinforcement learning setting. Applied to Sokoban, sliding block puzzle and robotic manipulation tasks, we show that the architecture can learn algorithmic solutions with strong generalization and abstraction: scaling to arbitrary task configurations and complexities, and being independent of both the data representation and the task domain.