Checklist 1. For all authors (a)

Do the main claims made in the abstract and introduction accurately reflect the paper's Did you discuss any potential negative societal impacts of your work? If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Y es] Code can be Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? Did you include the total amount of compute and the type of resources used (e.g., type Did you include any new assets either in the supplemental material or as a URL? [No] Did you discuss whether and how consent was obtained from people whose data you're If you used crowdsourcing or conducted research with human subjects... (a) Code was written in PyTorch (Paszke et al., 2019), and hyperparameters for regular (non SMC) methods were selected through grid search over a validation fold of the training data where appropriate. In Thomson et al. (2009), there was no BMI information, so we The simulations used for evaluating the methods were provided to us by Uster et al. (2021), who However, the simulation setup they use is not based on the underlying assumption that we make. These methods rely on some level of experience in the environment (mostly from expert demonstrations), and the challenge is clearly harder if given just suggestions from an expert policy.