39 citations · 107 across the 30 of their papers we have counts for
34 papers
MDP Planning as Policy Inference
David Tolpin
We formulate episodic Markov decision process (MDP) planning as Bayesian inference over policies. The primary contribution is conceptual: the policy itself is treated as the latent…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\mathc…
Neural Human Pose Prior
Michal Heker, Sefy Kagarlitsky, David Tolpin
We introduce a principled, data-driven approach for modeling a neural prior over human body poses using normalizing flows. Unlike heuristic or low-expressivity alternatives, our me…
Fast Neural Inverse Kinematics on Human Body Motions
David Tolpin, Sefy Kagarlitsky
Markerless motion capture enables the tracking of human motion without requiring physical markers or suits, offering increased flexibility and reduced costs compared to traditional…
Efficient Incremental Belief Updates Using Weighted Virtual Observations
David Tolpin
We present an algorithmic solution to the problem of incremental belief updating in the context of Monte Carlo inference in Bayesian statistical models represented by probabilistic…
Monitoring Time Series With Missing Values: a Deep Probabilistic Approach
Oshri Barazani, David Tolpin
Systems are commonly monitored for health and security through collection and streaming of multivariate time series. Advances in time series forecasting due to adoption of multilay…