3 papers
cs.LG2026
Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning
Faid Keddouri, Sohaib Houhou, Aissa Boulmerka +1
Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the train…
cs.LG2026
Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization
Kamar Hibatallah Baghdadi, Kawther Guoual Belhamidi, Sara Belhadj +2
We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decompose…
cs.LG2026
Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See
Mohamed Benabdelouahad, Ahmed Djalal Hacini, Nadir Farhi +1
We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that sha…