AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Learning to Follow Instructions in Text-Based Games

Mathieu Tuli, Andrew C Li, Pashootan Vaezipoor, Toryn Q. Klassen, Scott Sanner, Sheila A. McIlraith

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Language-grounded reinforcement agents · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Represent instructions as LTL and condition the policy on the instruction and its current progressed stateGATA on TextWorld Cooking · Cooking levels 0–3normalized game points and game success rateImproved
Remove LTL progression (ablation)LTL-GATA · TextWorld CookingperformanceHurt
Require GATA to examine the cookbook at the first step (ablation)GATA-D · TextWorld CookingperformanceNo clear effect
Use LTL reward without LTL-based episode termination (ablation)LTL-GATA · Cooking levels 1 and 2performanceImproved
Use LTL-based episode termination without LTL reward (ablation)LTL-GATA · Cooking levels 1 and 2performanceImproved
Remove both LTL reward and LTL-based episode termination (ablation)LTL-GATA · Cooking level 2, 20-game training setperformanceHurt
Represent LTL predicates as multiple tokens rather than single tokens (ablation)LTL-GATA · TextWorld Cooking, 20-game training setperformanceNo clear effect
Train GATA with instructions stripped from observations (ablation)GATA-D · Cooking levels 1 and 2normalized game points and success rateNo clear effect
Use 100 training games instead of 20 (ablation)LTL-GATA · TextWorld Cookingtest performanceImproved
Apply LTL-GATA to games with navigationLTL-GATA · Cooking level 3performance relative to GATAMixed
Use GPT-3 Da Vinci for few-shot natural-language-to-LTL translation instead of GPT-3 AdaGPT-3 · TextWorld observation-to-LTL translationtranslation correctness: 93.2% absolutely correctly and another 5.6% almost correctly; Ada translated all 100% of examples incorrectlyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy