AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Self-Supervised Reinforcement Learning that Transfers using Random Features

Boyuan Chen, Chuning Zhu, Pulkit Agrawal, Kaiqing Zhang, Abhishek Gupta

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models · 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
increase random feature dimension from 128 to 2048 (ablation)random-feature transfer method · Pointfinal return: 30.46 -> 34.01Improved
increase random feature dimension from 128 to 1024 (ablation)random-feature transfer method · Metaworld Reachfinal return: 765.38 -> 855.14Improved
increase random feature dimension from 128 to 512 (ablation)random-feature transfer method · Point Perturbedfinal return: 29.61 -> 33.13Improved
increase random feature dimension from 1024 to 2048 (ablation)random-feature transfer method · Metaworld Reachfinal return: 855.14 -> 830.84No clear effect
very high dimensional random features (ablation)random-feature transfer method · Point, Point Perturbed, Metaworld Reachadaptation speedHurt
use Gaussian matrix random features instead of NN random features (ablation)random-feature transfer method · Point and MetaWorld Reachreward approximation / returnHurt
use second-order polynomial features instead of NN random features (ablation)random-feature transfer method · Point and MetaWorld Reachreward approximation / returnMixed
use multi-step Q functions from random cumulants instead of dynamics model rollouts (ablation)random-feature transfer method · novel task at test timetruncated Q approximation errorImproved

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