Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The underlying principle of this type of approach is to maintain a Bayesian posterior over dynamics (conditioned on past experienced transitions) and to seek at each time step for the action optimizing the related augmented MDP (on state-history meta-states and related meta-dynamics), which is generally an intractable problem (for exact solving). This contribution relies on two previous ideas, simulation-based search (with root sampling, which avoids updating the belief over dynamics during planning) and value function approximation (which requires introducing proper features for handling histories), combining them to provide a new approach. In addition to this general approach, called BAFA, the authors provide an alternative and more general proof for the validity of root sampling and provide some experimental results. Overall, the paper is well written and clear, it proposes a sound approach, based on known ideas but combining them smartly (especially for the history features, which seems to be the newest part/the core contribution). My major comment is that experiences, if convincing, are not detailed enough to be reproducible (for example, some meta-parameters are not provided, nor discussed).