Gabriele Picco, Lam Thanh Hoang, et al.
EMNLP 2021
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 extracting first order logical facts from text observation and external word meaning network (ConceptNet), then training 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.
Gabriele Picco, Lam Thanh Hoang, et al.
EMNLP 2021
Chulaka Gunasekara, Guy Feigenblat, et al.
EMNLP 2021
Georgios Kollias, Payel Das, et al.
ICML 2024
Daiki Kimura, Tsunehiko Tanaka, et al.
NAACL 2022