AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Semantic Exploration from Language Abstractions and Pretrained Representations

Allison Tam, Neil Charles Rabinowitz, Andrew Kyle Lampinen, Nicholas Andrew Roy, Stephanie C.Y. Chan, DJ Strouse, Jane X Wang, Andrea Banino, Felix Hill

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 16 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
use CLIP/ALM text embeddings of oracle captions as NGU state instead of controllable stateNGU · City coveragecoverage (bins): 83 -> 241Improved
use pretrained CLIP/ALM image embeddings (LSE-NGU) instead of controllable stateNGU · City coveragecoverage (bins): 83 -> 162Improved
replace language-shaped image embeddings with ImageNet embeddings (ablation)LSE-NGU · City coveragecoverage (bins): 162 -> 111Hurt
use language oracle captions with random features (Lang-RND) instead of visual random features (ablation)RND · Playroom lift/putsample efficiency: 33% faster on liftImproved
semantic caption targets (LD) instead of shuffled statistically matched targets (S-LD) (ablation)language distillation · Playroom lift/put/findsample efficiencyImproved
pretrained language-shaped representations in NGU instead of Vis-NGUNGU · Playroom lift/put/findsample efficiency: 50-70% on lift/put, 18-38% on findImproved
ALM network distillation targets instead of random target (ND vs Vis-RND)RND · Playroom findsample efficiency: 41% fasterImproved
ImageNet embeddings instead of language-shaped embeddings in LSE-NGU (ablation)LSE-NGU · Playroom findsample efficiencyHurt
ImageNet embeddings instead of Vis-NGU controllable state (ablation)NGU · Playroom lift/putsample efficiencyImproved
freeze a pretrained inverse-dynamics model for controllable states in Vis-NGU (ablation)Vis-NGU · Playroomlearning speedNo 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