AINeutralarXiv – CS AI · Jun 256/10
🧠
Low-Complexity Policy Tessellations in Structured Markov Decision Processes
Researchers propose a novel approach to reinforcement learning that approximates optimal policies through geometric tessellations rather than high-dimensional value functions. The method demonstrates superior performance in structured decision problems like inventory control and queue admission, with faster error decay and greater stability compared to traditional RL baselines.