AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning

Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao, Alexander T Toshev, Sergey Levine, brian ichter

ICLR 2022 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 4 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 VFS instead of the strongest listed baselinemodel-free HRL · MultiRoom-10success rate: 0.43 -> 0.77Improved
Use VFS instead of the strongest listed baselinemodel-free HRL · KeyCorridor-7success rate: 0.54 -> 0.68Improved
Use VFS instead of CURLmodel-free HRL · KeyCorridor-3success rate: 0.83 -> 0.82No clear effect
Use VFS instead of a learned image representationmodel-based manipulation · O10task success rate: 2/20 -> 80%Improved
Combine learned representations with VFS by concatenating their embeddings (ablation)model-free HRL · MultiRoom-4 (SPL)SPL: 0.84 -> 0.90Improved
Combine learned representations with VFS by concatenating their embeddings (ablation)model-free HRL · KeyCorridor-7 (SPL)SPL: 0.59 -> 0.65Improved
Increase CURL embedding size from 1x to 5x (ablation)CURL · MultiRoom-10success rate: 0.43 -> 0.48Improved
Increase CURL embedding size from 1x to 5x (ablation)CURL · KeyCorridor-7success rate: 0.54 -> 0.56Improved
Increase VAE embedding size from 1x to 5x (ablation)VAE · MultiRoom-10success rate: 0.58 -> 0.62Improved
Increase VAE embedding size from 1x to 5x (ablation)VAE · KeyCorridor-7success rate: 0.50 -> 0.53Improved
Increase AE embedding size from 1x to 2x (ablation)AE · MultiRoom-10success rate: 0.34 -> 0.33Hurt
Increase AE embedding size from 1x to 5x (ablation)AE · KeyCorridor-7success rate: 0.33 -> 0.40Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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