AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

What Reward Structure Enables Efficient Sparse-Reward RL? A Proof-of-Concept with Policy-Aware Matrix Completion

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Reward shaping for sparse rewards

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 inverse propensity weighting (ablation)PAMC · Atari (26 games)human-normalized score: 1.15 -> 1.42Improved
add PAMC reward completion to DrQ-v2DrQ-v2 · Montezuma's Revenge (10M steps)return: 200 ± 50 -> 4100 ± 250Improved
add PAMC to DrQ-v2DrQ-v2 · Atari (26 games)human-normalized score: 1.25 ± 0.05 -> 1.51 ± 0.05Improved
add PAMC to MT-SACMT-SAC · MetaWorld-50success rate: 0.65 ± 0.03 -> 0.78 ± 0.02Improved
add PAMC to DreamerV3DreamerV3 · DM Controlreturn: 820 ± 16 -> 921 ± 17Improved
apply PAMC on dense-reward Walker-WalkPAMC · Walker-Walkreturn: 920 ± 30 -> 950 ± 25No clear effect
apply PAMC on high-rank hashed reward controls (ablation)PAMC · high-rank hash-rewardreturnNo clear effect
reduce rank by coarse discretization (ablation)PAMC · reward matrixreturnNo clear effect
apply PAMC to D4RL MuJoCo with CQLCQL · D4RL MuJoCoreturn: +15%Improved
corrupt propensities with sigma 0.3 noise (ablation)PAMC · Atari HNSHNS: -8%Hurt

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