AI Paper Atlas

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

Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents

Wenlong Huang, Fei Xia, Dhruv Shah, Danny Driess, Andy Zeng, Yao Lu, Pete Florence, Igor Mordatch, Sergey Levine, Karol Hausman, brian ichter

NeurIPS 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning

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
add grounded decoding (greedy) to LLM plannerLLM planner + CLIPort · Tabletop unseen Letterssuccess rate: 19% -> 37%Improved
add grounded decoding (greedy) to LLM plannerLLM planner + CLIPort · Tabletop seen Box Packingsuccess rate: 11% -> 78%Improved
use beam search instead of greedy decoding (ablation)GD · Tabletop seen Blocks & Bowlssuccess rate: 60% -> 77%Improved
use beam search instead of greedy decoding (ablation)GD · Tabletop seen Box Packingsuccess rate: 79 -> 78%No clear effect
use beam search instead of greedy decoding (ablation)GD · Tabletop unseen Blocks & Bowlssuccess rate: 44% -> 50%Improved
plan with LLM instead of end-to-end CLIPort (Long)CLIPort · Tabletop unseen Letterssuccess rate: 10% -> 19%Improved
add grounded decoding (greedy) to LLM plannerLLM planner + PPO skills · 2D Maze Hardsuccess rate: 54% -> 78%Improved
use beam search instead of greedy decoding (ablation)GD · 2D Maze Hardsuccess rate: 78% -> 88%Improved
use beam search instead of greedy decoding (ablation)GD · 2D Maze Easysuccess rate: 100% -> 100%No clear effect
hierarchical LLM planning instead of hierarchical RLHRL · 2D Maze Mediumsuccess rate: 48% -> 87%Improved
use GD with open-vocabulary detector chain-of-thought instead of SayCanSayCan · Kitchen ambiguousplanning success rate: 33% -> 58%Improved
use GD instead of SayCan on unambiguous tasksSayCan · Kitchen unambiguousplanning success rate: 85% -> 85%No clear effect

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