AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

Aravind Venugopal, Jiayu Chen, Xudong Wu, Chongyi Zheng, Benjamin Eysenbach, Jeff Schneider

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals · 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
add occupancy reward shaping (ORS) to GCIQLGCIQL · OGBench mean over 13 datasetssuccess rate (%): 20.0 -> 44.2Improved
use occupancy-based instead of graph-based reward shapingGo-Fresh · OGBench mean over 13 datasetssuccess rate (%): 35.8 -> 44.2Improved
use occupancy-based reward shaping instead of hierarchical policyHIQL · OGBench antmaze-giant-navigatesuccess rate (%): 72 -> 56Hurt
use ORS instead of Go-FreshGo-Fresh · OGBench antmaze-large-exploresuccess rate (%): 38 -> 22Hurt
use ORS reward instead of L2 distance reward (ablation)ORS · OGBench antmaze-giant-navigatesuccess rate (%): 3 -> 56Improved
use ORS reward instead of L2 distance reward (ablation)ORS · OGBench cube-triple-playsuccess rate (%): 3 -> 37Improved
add L2 distance reward to GCIQL (ablation)GCIQL · OGBench cube-triple-playsuccess rate (%): 7 -> 3Hurt
learn Q as cumulative sum of state-action reward (vs ORS-s / ORS-r variants) (ablation)ORS · OGBench scene-playsuccess rate (%)Improved
lower expectile kappa from 0.9 to 0.6 (ablation)ORS · OGBench antmaze-giant-navigatesuccess rate (%): 1 -> 56Improved
lower expectile kappa from 0.9 to 0.6 (ablation)ORS · OGBench puzzle-4x4-playsuccess rate (%): 21 -> 70Improved
raise expectile kappa from 0.6 to 0.9 (ablation)ORS · OGBench cube-triple-playsuccess rate (%): 4 -> 37Improved
raise expectile kappa from 0.6 to 0.75 (ablation)ORS · OGBench scene-playsuccess rate (%): 70 -> 80Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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