[PDF][PDF] Mitigating gradient bias in multi-objective learning: A provably convergent approach

H Fernando, H Shen, M Liu, S Chaudhury… - 2023 - par.nsf.gov
Machine learning problems with multiple objectives appear either i) in learning with multiple
criteria where learning has to make a trade-off between multiple performance metrics such …

Three-way trade-off in multi-objective learning: Optimization, generalization and conflict-avoidance

L Chen, H Fernando, Y Ying… - Advances in Neural …, 2023 - proceedings.neurips.cc
Multi-objective learning (MOL) often arises in emerging machine learning problems when
multiple learning criteria or tasks need to be addressed. Recent works have developed …

Anchor-changing regularized natural policy gradient for multi-objective reinforcement learning

R Zhou, T Liu, D Kalathil… - Advances in neural …, 2022 - proceedings.neurips.cc
We study policy optimization for Markov decision processes (MDPs) with multiple reward
value functions, which are to be jointly optimized according to given criteria such as …

Preparing for black swans: The antifragility imperative for machine learning

M ** - ar** for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach
D Kim, H Kwon, J Kim, G Lee, S Oh - arxiv preprint arxiv:2409.15755, 2024 - arxiv.org
As the complexity of tasks addressed through reinforcement learning (RL) increases, the
definition of reward functions also has become highly complicated. We introduce an RL …

Risk-sensitive bayesian games for multi-agent reinforcement learning under policy uncertainty

H Eriksson, D Basu, M Alibeigi… - arxiv preprint arxiv …, 2022 - arxiv.org
In stochastic games with incomplete information, the uncertainty is evoked by the lack of
knowledge about a player's own and the other players' types, ie the utility function and the …

C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front

R Liu, Y Pan, L Xu, L Song, P You, Y Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Multi-objective reinforcement learning (MORL) excels at handling rapidly changing
preferences in tasks that involve multiple criteria, even for unseen preferences. However …

Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond

W Chen, X Zhang, B Lin, X Lin, H Zhao… - arxiv preprint arxiv …, 2025 - arxiv.org
Multi-objective optimization (MOO) in deep learning aims to simultaneously optimize
multiple conflicting objectives, a challenge frequently encountered in areas like multi-task …