AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems

Jonathan Colaço Carr, Prakash Panangaden, Doina Precup, Benjamin Van Roy

ICML 2026 · Reinforcement learning › MDPs and planning · approach: POMDPs and confounded RL · 0 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 HPI instead of SPPO for pairwise-preference RLHPI · Mujoco-v5 suite and Mujoco-NT (13 tasks, true preference margin)AUC confidence interval vs SPPO: 12/13 tasks exceed or overlap SPPOImproved
use HPI-Clip instead of SPPOHPI-Clip · Mujoco-v5 suite and Mujoco-NT (13 tasks, true preference margin)AUC confidence interval vs SPPO: 12/13 tasks exceed or overlap SPPOImproved
use HPI-Clip instead of SPPO on nontransitive preference marginsHPI-Clip · Mujoco-NT (Reacher-NT, Walker2d-NT)AUC of inverted optimality gap: strictly higher CI on both tasksImproved
use HPI-Clip instead of SPPO with learned preference models (ablation)HPI-Clip · Mujoco-v5 suite (learned preference model)AUC confidence interval vs SPPO: better on 7 of 11 tasks, worse on 1 of 11Improved
use HPI instead of SPPO with learned preference models (ablation)HPI · Mujoco-v5 suite (learned preference model)AUC confidence interval vs SPPO: better on 8 of 11 tasks, worse on 1 of 11Improved
use HPI and HPI-Clip instead of SPPO with learned preference models (ablation)HPI, HPI-Clip · Mujoco-NT (learned preference model)AUC confidence interval vs SPPO: strictly higher CI on both tasksImproved
increase the comparison horizon TC (average the preference cumulant over more timesteps, towards SPPO) (ablation)SPPO variants vs HPI-Clip · Mujoco taskslearning efficiencyHurt

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