AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning

Ying-Tu Chen, Wei Hung, Bing-Shu Wu, Zhang-Wei Hong, Ping-Chun Hsieh

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 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
add preference-guided z sampling (PG-Explore) instead of standard normal z (ablation)MORL-FB · MO-Gymnasium Ant3dutility and hypervolumeImproved
add auxiliary Q loss on observed reward vectors (ablation)MORL-FB · MO-Gymnasium Ant3dutility and hypervolumeImproved
use MORL-FB instead of vanilla FBforward-backward RFRL · MO-Gymnasium continuous controlutility, hypervolume, episodic dominanceImproved
use MORL-FB instead of PD-MORL and Q-PensieveMORL baselines · MO-Gymnasium continuous controlutility, hypervolume, EDImproved
train only on one-hot and uniform preferencesMORL-FB · MO-Gymnasium continuous control, limited training preferencesutility, hypervolume, EDNo clear effect
transfer from Hopper2d to Hopper3d/4d zero-shot with MORL-FB instead of vanilla FBforward-backward RFRL · Hopper cross-objective transferreturnImproved

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