Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning. (arXiv:2108.03706v3 [stat.ML] UPDATED)

The recent emergence of reinforcement learning has created a demand for
robust statistical inference methods for the parameter estimates computed using
these algorithms. Existing methods for statistical inference in online learning
are restricted to settings involving independently sampled observations, while
existing statistical inference methods in reinforcement learning (RL) are
limited to the batch setting. The online bootstrap is a flexible and efficient
approach for statistical inference in linear stochastic approximation
algorithms, but its efficacy in settings involving Markov noise, such …

arxiv bootstrap evaluation inference learning ml policy reinforcement reinforcement learning