AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning

Jianda Chen, Sinno Pan

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 1 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 RAP behavioral metric instead of DrQ augmentationSAC · Robosuite Door Openingepisode return: 14.63 -> 102.19Improved
use RAP instead of DBCSAC · Robosuite Two Arm Peg-In-Holeepisode return: 219.56 -> 307.27Improved
use RAP instead of MICoSAC · Robosuite Door Openingepisode return: 6.06 -> 102.19Improved
add RAP representation loss to plain SACSAC · Robosuite Door Openingepisode return: 8.84 -> 102.19Improved
add RAP loss vs plain SACSAC · Robosuite Two Arm Peg-In-Holeepisode return: 191.29 -> 307.27Improved
compare RAP with DrQ augmentationSAC · DMC original backgroundepisode returnNo clear effect
use RAP vs DBC and MICo with natural video backgroundSAC · DMC natural video backgroundepisode returnImproved
compare RAP with DrQ with natural video backgroundSAC · DMC natural video backgroundepisode returnMixed
use RAP vs DBC and MICoSAC · CARLAepisode returnImproved
compare RAP with DrQSAC · CARLAepisode returnNo 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