About me
I am a Ph.D. candidate at the Technion, advised by Prof. Aviv Tamar in the RL^2 lab . In my research, I develop reinforcement-learning (RL) motion planning algorithms for robotic manipulators. Previously, I was a CS M.Sc student at Tel-Aviv University advised by Prof. Yishay Mansour working on theoretical machine learning.

Sub-Goal Trees – a Framework for Goal-Based Reinforcement Learning

Many AI problems, in robotics and other domains, are goal-based, essentially seeking trajectories leading to various goal states. Reinforcement learning (RL), building on Bellman’s optimality equation, naturally optimizes for a single goal, yet can be made multi-goal by augmenting the state with the goal. Instead, we propose a new RL framework, derived from a dynamic programming equation for the all pairs shortest path (APSP) problem, which naturally solves multigoal queries. We show that this approach has computational benefits for both standard and approximate dynamic programming. Interestingly, our formulation prescribes a novel protocol for computing a trajectory: instead of predicting the next state given its predecessor, as in standard RL, a goal-conditioned trajectory is constructed by first predicting an intermediate state between start and goal, partitioning the trajectory into two. Then, recursively, predicting intermediate points on each sub-segment, until a complete trajectory is obtained. We call this trajectory structure a subgoal tree. Building on it, we additionally extend the policy gradient methodology to recursively predict sub-goals, resulting in novel goal-based algorithms. Finally, we apply our method to neural motion planning, where we demonstrate significant improvements compared to standard RL on navigating a 7-DoF robot arm between obstacles.

Harnessing Reinforcement Learning for Neural Motion Planning

In this work, we trained deep learning models to spatially resolve bulk mRNA and miRNA expression levels on pathology whole-slide images. Our models reach up to 0.95 AUC on held-out test sets from two cancer cohorts using a simple training pipeline and a small number of training samples. We also developed a method to spatially characterize tumor heterogeneity from the predicted gene expression levels. Applying our methods to breast and lung cancer slides, we discovered a significant statistical link between heterogeneity and survival. This project was supported by the European Union's Horizon 2020 and Google Cloud funding.

Learning Decision Trees with Stochastic Linear Classifiers

In this work we propose a top-down decision tree learning algorithm with a class of linear classifiers called stochastic linear classifiers as the internal nodes’ hypothesis class. To this end, we derive efficient algorithms for minimizing the Gini index for this class for each internal node, although the problem is non-convex. Moreover, the proposed algorithm has a theoretical guarantee under the weak stochastic hypothesis assumption.