Instance-Dependent Confidence and Early Stopping for Reinforcement Learning. (arXiv:2201.08536v1 [stat.ML])

Web: http://arxiv.org/abs/2201.08536

Various algorithms for reinforcement learning (RL) exhibit dramatic variation
in their convergence rates as a function of problem structure. Such
problem-dependent behavior is not captured by worst-case analyses and has
accordingly inspired a growing effort in obtaining instance-dependent
guarantees and deriving instance-optimal algorithms for RL problems. This
research has been carried out, however, primarily within the confines of
theory, providing guarantees that explain \textit{ex post} the performance
differences observed. A natural next step is to convert these theoretical
guarantees into …

arxiv confidence learning ml reinforcement learning