Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning

TL;DR

This paper reformulates Interactive Fiction game playing as a Multi-Passage Reading Comprehension task, leveraging attention mechanisms and structured prediction to improve game-solving performance with less data.

Contribution

It introduces a novel approach that models IF game playing as MPRC, utilizing context-query attention and object-centric retrieval to enhance understanding and action generation.

Findings

Achieves higher winning rates on Jericho benchmark

Requires less training data than previous methods

Demonstrates effectiveness of MPRC formulation in IF games

Abstract

Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. In contrast to previous text games with mostly synthetic texts, IF games pose language understanding challenges on the human-written textual descriptions of diverse and sophisticated game worlds and language generation challenges on the action command generation from less restricted combinatorial space. We take a novel perspective of IF game solving and re-formulate it as Multi-Passage Reading Comprehension (MPRC) tasks. Our approaches utilize the context-query attention mechanisms and the structured prediction in MPRC to efficiently generate and evaluate action outputs and apply an object-centric historical observation retrieval strategy to mitigate the partial observability of the textual observations. Extensive experiments on the recent IF benchmark (Jericho) demonstrate clear advantages of our approaches achieving high winning rates and low data requirements compared to all previous approaches. Our source code is available at: https://github.com/XiaoxiaoGuo/rcdqn.