Skip to main content

🏢 MediaTek Research

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
·311 words·2 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 MediaTek Research
Novel optimistic RL algorithm using kernel methods achieves no-regret performance in the challenging infinite-horizon average-reward setting.
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
·2136 words·11 mins· loading · loading
AI Theory Optimization 🏢 MediaTek Research
Exact Gauss-Newton optimization in deep reversible networks surprisingly reveals poor generalization, despite faster training, challenging existing deep learning optimization theories.