Neural Logic Reinforcement Learning
This addresses generalization and interpretability issues in reinforcement learning for AI applications, though it is incremental as it builds on existing policy gradient and differentiable inductive logic programming methods.
The authors tackled the problems of poor generalization and lack of interpretability in deep reinforcement learning by proposing Neural Logic Reinforcement Learning (NLRL), which uses first-order logic to represent policies, achieving near-optimal performance and good generalizability in cliff-walking and blocks manipulation tasks.
Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor modifications of the training environment. Except that, the use of deep neural networks makes the learned policies hard to be interpretable. To address these two challenges, we propose a novel algorithm named Neural Logic Reinforcement Learning (NLRL) to represent the policies in reinforcement learning by first-order logic. NLRL is based on policy gradient methods and differentiable inductive logic programming that have demonstrated significant advantages in terms of interpretability and generalisability in supervised tasks. Extensive experiments conducted on cliff-walking and blocks manipulation tasks demonstrate that NLRL can induce interpretable policies achieving near-optimal performance while demonstrating good generalisability to environments of different initial states and problem sizes.