1k citations · 2k across the 65 of their papers we have counts for
35 papers · 1 filter
More with LESS -- Local Scene Representations for Tactile Imaging
Zohar Rimon, Elisei Shafer, Tal Tepper +4
Tactile imaging seeks to reconstruct the internal structure of soft objects through touch sensing, with applications in medical diagnosis and robotic manipulation. Recent self-supe…
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
Tal Daniel, Carl Qi, Dan Haramati +5
We introduce Latent Particle World Model (LPWM), a self-supervised object-centric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM aut…
Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion
Dan Haramati, Carl Qi, Tal Daniel +3
We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve l…
Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies
Zohar Rimon, Elisei Shafer, Tal Tepper +2
Palpation, the use of touch in medical examination, is almost exclusively performed by humans. We investigate a proof of concept for an artificial palpation method based on self-su…
A Classification View on Meta Learning Bandits
Mirco Mutti, Jeongyeol Kwon, Shie Mannor +1
Contextual multi-armed bandits are a popular choice to model sequential decision-making. E.g., in a healthcare application we may perform various tests to asses a patient condition…
Test-Time Regret Minimization in Meta Reinforcement Learning
Mirco Mutti, Aviv Tamar
Meta reinforcement learning sets a distribution over a set of tasks on which the agent can train at will, then is asked to learn an optimal policy for any test task efficiently. In…
MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
Zohar Rimon, Tom Jurgenson, Orr Krupnik +2
Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by lo…
Fine-Tuning Generative Models as an Inference Method for Robotic Tasks
Orr Krupnik, Elisei Shafer, Tom Jurgenson +1
Adaptable models could greatly benefit robotic agents operating in the real world, allowing them to deal with novel and varying conditions. While approaches such as Bayesian infere…
TGRL: An Algorithm for Teacher Guided Reinforcement Learning
Idan Shenfeld, Zhang-Wei Hong, Aviv Tamar +1
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential…
ContraBAR: Contrastive Bayes-Adaptive Deep RL
Era Choshen, Aviv Tamar
In meta reinforcement learning (meta RL), an agent seeks a Bayes-optimal policy -- the optimal policy when facing an unknown task that is sampled from some known task distribution.…
Explore to Generalize in Zero-Shot RL
Ev Zisselman, Itai Lavie, Daniel Soudry +1
We study zero-shot generalization in reinforcement learning-optimizing a policy on a set of training tasks to perform well on a similar but unseen test task. To mitigate overfittin…
Goal-Conditioned Supervised Learning with Sub-Goal Prediction
Tom Jurgenson, Aviv Tamar
Recently, a simple yet effective algorithm -- goal-conditioned supervised-learning (GCSL) -- was proposed to tackle goal-conditioned reinforcement-learning. GCSL is based on the pr…
Towards Deployable RL -- What's Broken with RL Research and a Potential Fix
Shie Mannor, Aviv Tamar
Reinforcement learning (RL) has demonstrated great potential, but is currently full of overhyping and pipe dreams. We point to some difficulties with current research which we feel…
Learning Control by Iterative Inversion
Gal Leibovich, Guy Jacob, Or Avner +2
We propose -- an algorithm for learning an inverse function without input-output pairs, but only with samples from the desired output distribution an…
Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach
Zohar Rimon, Aviv Tamar, Gilad Adler
In meta reinforcement learning (meta RL), an agent learns from a set of training tasks how to quickly solve a new task, drawn from the same task distribution. The optimal meta RL p…
Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability
Aviv Tamar, Daniel Soudry, Ev Zisselman
In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimi…
Unsupervised Feature Learning for Manipulation with Contrastive Domain Randomization
Carmel Rabinovitz, Niko Grupen, Aviv Tamar
Robotic tasks such as manipulation with visual inputs require image features that capture the physical properties of the scene, e.g., the position and configuration of objects. Rec…
Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder
Tal Daniel, Aviv Tamar
The recently introduced introspective variational autoencoder (IntroVAE) exhibits outstanding image generations, and allows for amortized inference using an image encoder. The main…
Online Safety Assurance for Deep Reinforcement Learning
Noga H. Rotman, Michael Schapira, Aviv Tamar
Recently, deep learning has been successfully applied to a variety of networking problems. A fundamental challenge is that when the operational environment for a learning-augmented…
Offline Meta Learning of Exploration
Ron Dorfman, Idan Shenfeld, Aviv Tamar
Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of conventional RL agents, trained on different…
Deep Residual Flow for Out of Distribution Detection
Ev Zisselman, Aviv Tamar
The effective application of neural networks in the real-world relies on proficiently detecting out-of-distribution examples. Contemporary methods seek to model the distribution of…
Deep Variational Semi-Supervised Novelty Detection
Tal Daniel, Thanard Kurutach, Aviv Tamar
In anomaly detection (AD), one seeks to identify whether a test sample is abnormal, given a data set of normal samples. A recent and promising approach to AD relies on deep generat…
Sub-Goal Trees -- a Framework for Goal-Directed Trajectory Prediction and Optimization
Tom Jurgenson, Edward Groshev, Aviv Tamar
Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a…
Multi-Agent Reinforcement Learning with Multi-Step Generative Models
Orr Krupnik, Igor Mordatch, Aviv Tamar
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the s…