mlsanityData to 14 Oct 2026

Unlearning Works Better Than You Think: Local Reinforcement-Based Selection of Auxiliary Objectives

arXiv 2504.14418 ↗First posted 19 Apr 2025cs.NE stat.MLcited by 0

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

Abstract (arXiv)

We introduce Local Reinforcement-Based Selection of Auxiliary Objectives (LRSAO), a novel approach that selects auxiliary objectives using reinforcement learning (RL) to support the optimization process of an evolutionary algorithm (EA) as in EA+RL framework and furthermore incorporates the ability to unlearn previously used objectives. By modifying the reward mechanism to penalize moves that do no increase the fitness value and relying on the local auxiliary objectives, LRSAO dynamically adapts its selection strategy to optimize performance according to the landscape and unlearn previous objectives when necessary. We analyze and evaluate LRSAO on the black-box complexity version of the non-monotonic Jump function, with gap parameter ℓ, where each auxiliary objective is beneficial at specific stages of optimization. The Jump function is hard to optimize for evolutionary-based algorithms and the best-known complexity for reinforcement-based selection on Jump was O(n2 log(n) / ℓ). Our approach improves over this result to achieve a complexity of Theta(n2 / ℓ2 + n log(n)) resulting in a significant improvement, which demonstrates the efficiency and adaptability of LRSAO, highlighting its potential to outperform traditional methods in complex optimization scenarios.

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 5 of its 31 references that are in the map. First posted on arXiv 19 Apr 2025.

Builds on

5 of 31 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms22 Jan

Other references · 4

  1. 2023Evolutionary Reinforcement Learning: A Surveycited by 29
  2. 2023Reinforcement Learning-assisted Evolutionary Algorithm: A Survey and Research Opportunitiescited by 8
  3. 2021An Extended Jump Functions Benchmark for the Analysis of Randomized Search Heuristicscited by 3
  4. 2024Hyper-Heuristics Can Profit From Global Variation Operatorscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
  2. 2024Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning
  3. 2026A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
  4. 2024Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives
  5. 2025Evolutionary Policy Optimization
  6. 2026On the Runtime Analysis of Reinforcement Learning Hyper-Heuristics
  7. 2025Evolutionary Policy Optimization
  8. 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems