AICLLGROOct 21, 2021

LOA: Logical Optimal Actions for Text-based Interaction Games

arXiv:2110.10973v1712 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the challenge of interpretability and performance in AI agents for natural language games, though it appears incremental as it builds on existing neuro-symbolic approaches.

The paper tackles the problem of action decision in text-based interaction games by introducing Logical Optimal Actions (LOA), a neuro-symbolic reinforcement learning architecture that combines neural networks with symbolic knowledge acquisition, and demonstrates it through a web-based platform with comparisons to other agents.

We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. The demonstration for LOA experiments consists of a web-based interactive platform for text-based games and visualization for acquired knowledge for improving interpretability for trained rules. This demonstration also provides a comparison module with other neuro-symbolic approaches as well as non-symbolic state-of-the-art agent models on the same text-based games. Our LOA also provides open-sourced implementation in Python for the reinforcement learning environment to facilitate an experiment for studying neuro-symbolic agents. Code: https://github.com/ibm/loa

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes