AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Fine-tuning Behavioral Cloning Policies with Preference‑Based Reinforcement Learning

Mael Macuglia, Paul Friedrich, Giorgia Ramponi

ICLR 2026 · Reinforcement learning › Offline RL · approach: Diffusion models for offline decision making · 2 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
increase offline expert trajectories from 10 to 1000 (ablation)BRIDGE · Gridworld (clean demos)confidence set size (%): 99.9 -> 8.0Improved
reduce demonstration noise from 20% to 0% at 1000 trajectories (ablation)BRIDGE · Gridworldconfidence set size (%): 95.4 -> 8.0Improved
add offline-constrained confidence set vs pure online PbRLBRIDGE · StarMDP, Gridworld, Reacher, Antcumulative regretImproved
shrink confidence radius too far (ablation)BRIDGE · ReacherregretMixed
increase offline trajectories (ablation)BRIDGE · ReacherregretImproved
use embedding closer to true reward (reacher_reward) (ablation)BRIDGE · ReacherregretImproved

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