3 papers
cs.AI2026
Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation
Gijs Kassenaar, Zhao Yang, Vincent François-Lavet
Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which can lead to over-computatio…
cs.LG2026
Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
Qi Wei, Junchao Fan, Zhao Yang +3
Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment.…
cs.LG2025
Hadamax Encoding: Elevating Performance in Model-Free Atari
Jacob E. Kooi, Zhao Yang, Vincent François-Lavet
Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small…