Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

Automated news aggregation. Headlines and summaries are gathered from public feeds; see our editorial standards for sourcing, corrections, and AI-assist disclosure.

arXiv:2608.07725v1 Announce Type: new Abstract: Average-reward reinforcement-learning regret is known up to logarithmic factors, but the numerical content of published guarantees is difficult to compare because probability mode, structural parameter, logarithmic normalization, prior information, and planning assumptio…