AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Reinforcement Learning with Neural Radiance Fields

Danny Driess, Ingmar Schubert, Pete Florence, Yunzhu Li, Marc Toussaint

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 15 citations (OpenAlex)

Read the paper

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 compositional NeRF supervision instead of other learned representations or expert keypointsNeRF-RL · Mug on Hook, Planar Pushing, Door Openingsuccess rateImproved
Use a compositional NeRF decoder rather than a 2D CNN decoderNeRF-RL state representation · Mug on Hook, Planar Pushing, Door Openingsuccess rateImproved
Use the 3D neural field encoder instead of the 2D CNN image encoder (ablation)NeRF-RL with compositional NeRF decoder · Door Openingsuccess rateImproved
Use the 2D CNN image encoder instead of the 3D neural field encoder (ablation)NeRF-RL with compositional NeRF decoder · Mug on Hook, Planar Pushingsuccess rateNo clear effect
Replace compositional NeRF supervision with multi-view contrastive learningNeRF-RL representation learning · Mug on Hook, Planar Pushing, Door Openingsuccess rateHurt
Use CURL with image-cropping augmentation instead of NeRF supervisionRL state representation · Door Openingsuccess rateImproved
Use CURL with image-cropping augmentation instead of NeRF supervisionRL state representation · Planar Pushingsuccess rateHurt
Use CURL with image-cropping augmentation instead of NeRF supervisionRL state representation · Mug on Hooksuccess rate: 59%Mixed
Use a global NeRF decoder instead of a compositional NeRF decoder (ablation)NeRF-RL with image encoder · Planar Pushingsuccess rateHurt
Use a global NeRF decoder instead of a compositional NeRF decoder (ablation)NeRF-RL with image encoder · Door Openingsuccess rateHurt
Use compositionality in a convolutional autoencoder without NeRF supervision (ablation)Convolutional autoencoder · Mug on Hook, Planar Pushing, Door Openingsuccess rateHurt
Train the NeRF-RL representation for more epochs to improve reconstruction quality (ablation)NeRF-RL compositional + image · Mug on Hooksuccess rateImproved

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