ServiceNow recherche

Language Decision Transformers with Exponential Tilt for Interactive Text Environments

Résumé

Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards. We address these challenges by proposing Language Decision Transformers (LDTs), a framework that is based on transformer language models and decision transformers (DTs). Our LDTs extend DTs with 3 components: (1) exponential tilt to guide the agent towards high obtainable goals, (2) novel goal conditioning methods yielding better results than the traditional return-to-go (sum of all future rewards), and (3) a model of future observations that improves agent performance. LDTs are the first to address offline RL with DTs on these challenging games. Our experiments show that LDTs achieve the highest scores among many different types of agents on some of the most challenging Jericho games, such as Enchanter.

Publication
ArXiv
Nicolas Gontier
Nicolas Gontier
Research Scientist

Research Scientist at AI Frontier Research located at Montreal, QC, Canada.

Issam H. Laradji
Issam H. Laradji
Research Manager

Research Manager at AI Frontier Research located at Vancouver, BC, Canada.

David Vazquez
David Vazquez
Director of AI Research

Director of AI Research at AI Research Management located at Montreal, QC, Canada.

Christopher Pal
Christopher Pal
Distinguished Scientist

Distinguished Scientist at AI Research Partnerships & Ecosystem​ located at Montreal, QC, Canada.