mlsanityData to 14 Oct 2026

UCB-driven Utility Function Search for Multi-objective Reinforcement Learning

arXiv 2405.00410 ↗First posted 1 May 2024cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours that trade-off between multiple, possibly conflicting, objectives. MORL based on decomposition is a family of solution methods that employ a number of utility functions to decompose the multi-objective problem into individual single-objective problems solved simultaneously in order to approximate a Pareto front of policies. We focus on the case of linear utility functions parametrised by weight vectors w. We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process, with the aim of maximising the hypervolume of the resulting Pareto front. The proposed method demonstrates consistency and strong performance across various MORL baselines on Mujoco benchmark problems. The code is released in: https://github.com/SYCAMORE-1/ucb-MOPPO

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 40 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

17 of 40 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  4. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  5. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  6. 2019A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptationcited by 177
  7. 2019Reward-Conditioned Policiescited by 102
  8. 2018Dynamic Weights in Multi-Objective Deep Reinforcement Learningcited by 100
  9. 2019Deep Reinforcement Learning for Multi-objective Optimizationcited by 90
  10. 2016Multi-Objective Deep Reinforcement Learningcited by 83
  11. 2020Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewardscited by 60
  12. 2022PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithmcited by 58
5 more
  1. 2023Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritizationcited by 48
  2. 2018Meta-Learning for Multi-objective Reinforcement Learningcited by 34
  3. 2023Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Frameworkcited by 31
  4. 2023Evolutionary Reinforcement Learning: A Surveycited by 29
  5. 2022Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approachcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
  2. 2024Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
  3. 2025Preference-based Multi-Objective Reinforcement Learning
  4. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL
  5. 2024Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning
  6. 2025Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments
  7. 2024In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
  8. 2024Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity