Showing 2025Show all
3 papers · 1 filter
cs.LG2025
Statistical Guarantees for Offline Domain Randomization
Arnaud Fickinger, Abderrahim Bendahi, Stuart Russell
Reinforcement-learning (RL) agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR)…
cs.NE2025
Speeding Up Hyper-Heuristics With Markov-Chain Operator Selection and the Only-Worsening Acceptance Operator
Abderrahim Bendahi, Benjamin Doerr, Adrien Fradin +1
The move-acceptance hyper-heuristic was recently shown to be able to leave local optima with astonishing efficiency (Lissovoi et al., Artificial Intelligence (2023)). In this work,…
cs.NE2025
Unlearning Works Better Than You Think: Local Reinforcement-Based Selection of Auxiliary Objectives
Abderrahim Bendahi, Adrien Fradin, Matthieu Lerasle
We introduce Local Reinforcement-Based Selection of Auxiliary Objectives (LRSAO), a novel approach that selects auxiliary objectives using reinforcement learning (RL) to support th…