Interactive Fiction Games: A Colossal Adventure

Abstract

A hallmark of human intelligence is the ability to understand and communicate with language. Interactive Fiction games are fully text-based simulation environments where a player issues text commands to effect change in the environment and progress through the story. We argue that IF games are an excellent testbed for studying language-based autonomous agents. In particular, IF games combine challenges of combinatorial action spaces, language understanding, and commonsense reasoning. To facilitate rapid development of language-based agents, we introduce Jericho, a learning environment for man-made IF games and conduct a comprehensive study of text-agents across a rich set of games, highlighting directions in which agents can improve.

References in corpus (13)

• Efficient Estimation of Word Representations in Vector Space
• Prioritized Experience Replay
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Unifying Count-Based Exploration and Intrinsic Motivation
• Go-Explore: a New Approach for Hard-Exploration Problems
• Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
• TextWorld: A Learning Environment for Text-based Games
• Counting to Explore and Generalize in Text-based Games
• NAIL: A General Interactive Fiction Agent
• Backplay: "Man muss immer umkehren"
• Interactive Language Learning by Question Answering
• Comprehensible Context-driven Text Game Playing
• The Text-Based Adventure AI Competition

Cited by in corpus (6)

• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
• Aligning AI With Shared Human Values
• How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents
• Deriving Commonsense Inference Tasks from Interactive Fictions
• Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
• Towards LLM-Based Automatic Playtest