Neuro-Symbolic Reinforcement Learning with First-Order Logic
This addresses the need for faster and more interpretable policies in reinforcement learning for text-based games, though it is incremental as it builds on existing neuro-symbolic frameworks.
The authors tackled the problem of slow convergence and lack of interpretability in deep reinforcement learning by proposing a neuro-symbolic RL method using first-order logic and Logical Neural Networks for text-based games, resulting in significantly faster training convergence compared to other state-of-the-art neuro-symbolic methods on a TextWorld benchmark.
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with directly interpretable logical operators. Our experimental results show RL training with the proposed method converges significantly faster than other state-of-the-art neuro-symbolic methods in a TextWorld benchmark.