227 citations · 246 across the 47 of their papers we have counts for
36 papers · 1 filter
Learning Graded Sparse Mechanisms: A Representation Theorem and Certified Generalization
Mark Kozdoba, Shie Mannor
In a variety of multi-agent and physical environments, an element's update depends strongly on a few other elements and weakly on many, and both the identity and the number of the…
Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair
Elad Sharony, Ido Greenberg, Jialin Song +3
Large language model (LLM) code-repair systems fix faulty programs by repeatedly generating and testing revisions. Each revision is costly, making the choice of which repair to pur…
Reinforcement Learning with Segment Reward Feedback under Linear Function Approximation
Fengxu Liu, Siwei Wang, Gal Dalal +2
Classical reinforcement learning (RL) assumes that a reward is observed for every visited state-action pair. However, in real-world applications such as autonomous driving, such fi…
COMPASS: Ordered Clustered Routing at 100K Scale
Ido Greenberg, Hugo Linsenmaier, Piotr Sielski +4
Large-scale routing often requires visiting clusters of nodes in a prescribed order, giving rise to the Ordered Clustered Traveling Salesman Problem (OCTSP). Optimizing each cluste…
Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems
Mark Kozdoba, Shie Mannor
Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show that on syst…
Zero-Shot Active Feature Acquisition via LLM-Elicitation
Binyamin Perets, Natalie Mendelson, Shiran Vainberg +3
Active feature acquisition (AFA) sequentially selects which features to observe to reach a classification or ranking decision. Its central limitation is reliance on large amount of…
How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
Mark Kozdoba, Shie Mannor
Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example.In the wid…
The Value of Mechanistic Priors in Sequential Decision Making
Itai Shufaro, Gal Benor, Shie Mannor
Hybrid mechanistic models, physical priors with learned residuals, promise to reduce the data required for good decisions, but have no computable criterion to test this. We charact…
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
Lior Cohen, Ofir Nabati, Kaixin Wang +2
We study diffusion-based world models for reinforcement learning, which offer high generative fidelity but face critical efficiency challenges in control. Current methods either re…
VLM-Guided Experience Replay
Elad Sharony, Tom Jurgenson, Orr Krupnik +2
Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) have enabled powerful semantic and multimodal reasoning capabilities, creating new opportunities t…
Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum
Navdeep Kumar, Tehila Dahan, Lior Cohen +4
We establish an optimal sample complexity of for obtaining an -optimal global policy using a single-timescale actor-critic (AC) algorithm in infinite-horizon discoun…
Representative Action Selection for Large Action Space: From Bandits to MDPs
Quan Zhou, Shie Mannor
We study the problem of selecting a small, representative action subset from an extremely large action space shared across a family of reinforcement learning (RL) environments -- a…
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
Haitong Ma, Ofir Nabati, Aviv Rosenberg +7
Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discre…
Spectral Bellman Method: Unifying Representation and Exploration in RL
Ofir Nabati, Bo Dai, Shie Mannor +1
Representation learning is critical to the empirical and theoretical success of reinforcement learning. However, many existing methods are induced from model-learning aspects, misa…
Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead
Uri Koren, Navdeep Kumar, Uri Gadot +3
Classical policy gradient (PG) methods in reinforcement learning frequently converge to suboptimal local optima, a challenge exacerbated in large or complex environments. This work…
State Entropy Regularization for Robust Reinforcement Learning
Yonatan Ashlag, Uri Koren, Mirco Mutti +3
State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studie…
Hierarchical Adversarial Bandits for Online Configuration Optimization
Gil Shabat, Chen Avin, Shie Mannor +3
Motivated by Online Configuration Optimization in large, dynamic parameter spaces, this work studies the nonstochastic multi-armed bandit (MAB) problem in metric action spaces with…
Representative Action Selection for Large Action Space Bandit Families
Quan Zhou, Mark Kozdoba, Shie Mannor
We study the problem of selecting a subset from a large action space shared by a family of bandits. In many natural situations, while the nominal set of actions is large, actions a…
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…
Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms
Ido Greenberg, Piotr Sielski, Hugo Linsenmaier +5
Vehicle Routing Problems (VRP) are an extension of the Traveling Salesperson Problem and are a fundamental NP-hard challenge in combinatorial optimization. Solving VRP in real-time…
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
Ron Vainshtein, Zohar Rimon, Shie Mannor +1
Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While exc…
Simulus: Combining Improvements in Sample-Efficient World Model Agents
Lior Cohen, Kaixin Wang, Bingyi Kang +2
World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements unrealized due to the significant expe…
Reinforcement Learning with Segment Feedback
Yihan Du, Anna Winnicki, Gal Dalal +2
Standard reinforcement learning (RL) assumes that an agent can observe a reward for each state-action pair. However, in practical applications, it is often difficult and costly to…
RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
Uri Gadot, Assaf Shocher, Shie Mannor +2
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an o…