AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

RD-HRL: Generating Reliable Sub-Goals for Long-Horizon Sparse-Reward Tasks

Yixiang Shan, Haipeng Liu, Ting Long, Yi Chang

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Subgoal generation for hierarchical RL

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 reliability-driven decision mechanism (transition-region targets) to HIQLHIQL · antmaze-ultra-diversenormalized score: 52.9 -> 81.1Improved
add reliability-driven decision mechanism to HIQLHIQL · CALVINnormalized score: 43.8 -> 68.8Improved
use transition regions as decision-level targets instead of state at t+2H (ablation)RD-HRL · antmaze-ultra-diversenormalized score: 59.8 -> 81.1Improved
keep high-level policy between TI module and low-level policy (ablation)RD-HRL · antmaze-ultra-diversenormalized score: 27.8 -> 81.1Improved
use Target Evaluation module instead of plain value V (ablation)RD-HRL · antmaze-ultra-diversenormalized score: 35.3 -> 81.1Improved
add cross-trajectory value update in TE module (ablation)RD-HRL · antmaze-ultra-diversenormalized score: 68.1 -> 81.1Improved
keep temporal abstraction in TE (RD-HRL-CU vs RD-HRL-TE) (ablation)RD-HRL · antmaze-ultra-diversenormalized score: 35.3 -> 68.1Improved
increase waysteps H for HIQL (ablation)HIQL · antmaze-ultra-play/diversenormalized scoreMixed
use transition-region targets in non-Euclidean manipulation (ablation)RD-HRL · CALVINnormalized score: 35.5 -> 68.8Improved
RD-HRL versus best baseline on kitchen-partialRD-HRL · kitchen-partialnormalized score: 75.0 -> 69.6Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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