Neuro-Symbolic Reinforcement Learning with First-Order Logic

10/21/2021
by   Daiki Kimura, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/03/2021

Reinforcement Learning with External Knowledge by using Logical Neural Networks

Conventional deep reinforcement learning methods are sample-inefficient ...
research
10/21/2021

LOA: Logical Optimal Actions for Text-based Interaction Games

We present Logical Optimal Actions (LOA), an action decision architectur...
research
07/05/2023

Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning

Text-based reinforcement learning agents have predominantly been neural ...
research
12/30/2022

Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search

Learning efficient and interpretable policies has been a challenging tas...
research
11/12/2022

Deep Reinforcement Learning with Vector Quantized Encoding

Human decision-making often involves combining similar states into categ...
research
06/24/2021

FF-NSL: Feed-Forward Neural-Symbolic Learner

Inductive Logic Programming (ILP) aims to learn generalised, interpretab...
research
03/30/2020

Agent57: Outperforming the Atari Human Benchmark

Atari games have been a long-standing benchmark in the reinforcement lea...

Please sign up or login with your details

Forgot password? Click here to reset