Or Avner

2 accepted papers

2023

Learning Control by Iterative Inversion

Gal Leibovich, Guy Jacob, Or Avner, Gal Novik, Aviv Tamar

ICML 2023poster

We propose *iterative inversion* - an algorithm for learning an inverse function without input-output pairs, but only with samples from the desired output distribution and access to the forward function. The key challenge is a *distribution shift* between the desired outputs and the outputs of an in…

Cited by 2 Source ↗PDF ↗Scholar ↗

2020

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

Tom Jurgenson, Or Avner, Edward Groshev, Aviv Tamar

ICML 2020poster

Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. Reinforcement learning (RL), building on Bellman’s optimality equation, naturally optimizes for a single goal, yet can be made goal-directed by augmenting the state with t…

Cited by 53 Source ↗PDF ↗code ↗Scholar ↗