Author feedback: I thank the authors for the feedback. The feedback was of high quality and satisfied my concerns. I suggest that, perhaps a compressed version, of "Explaining limitations of our work" from the author feedback, which I enjoyed reading, will be added to the final version of the paper. The paper "Sampling Networks and Aggregate Simulation for Online POMDP Planning" proposes a new solution to computing policies for large POMDP problems that is based on factorizing the belief distribution using a mean field approximation during planning and execution and extending aggregate simulation to POMDPs. In short, the proposed POMDP planner projects factorized beliefs forward in time forming at the same time a computational graph and then computes gradients backwards in time over the graph to improve the policy.

Partially observable Markov decision processes (POMDP) are a useful model for decision-making under partial observability and stochastic actions. Partially Observable Monte-Carlo Planning is an online algorithm for deciding on the next action to perform, using a Monte-Carlo tree search approach, based on the UCT (UCB applied to trees) algorithm for fully observable Markov-decision processes. POMCP develops an action-observation tree, and at the leaves, uses a rollout policy to provide a value estimate for the leaf. As such, POMCP is highly dependent on the rollout policy to compute good estimates, and hence identify good actions. Thus, many practitioners who use POMCP are required to create strong, domain-specific heuristics. In this paper, we model POMDPs as stochastic contingent planning problems. This allows us to leverage domain-independent heuristics that were developed in the planning community. We suggest two heuristics, the first is based on the well-known h_add heuristic from classical planning, and the second is computed in belief space, taking the value of information into account.