Adapting RFRL objectives as auxiliary tasks with preference-guided exploration outperforms prior MORL methods in performance and data efficiency on MO-Gymnasium tasks.
Since some MO MuJoCo rewards depend on both states and actions, we compare MORL-FB and the extended one
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
Adapting RFRL objectives as auxiliary tasks with preference-guided exploration outperforms prior MORL methods in performance and data efficiency on MO-Gymnasium tasks.