275 citations · 437 across the 32 of their papers we have counts for
34 papers
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…
Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning
Uri Berger, Gal Chechik, Gal Dalal
We introduce Self-Saliency, a method for training Vision-Language Models (VLMs) to increase the alignment between their visual attention and the image regions mentioned in their re…
More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
Gal Dalal, Assaf Hallak, Gal Chechik +1
Wider beam search should improve LLM reasoning, but when should you stop widening? Prior work on beam width selection has focused on inference efficiency \citep{qin2025dsbd, freita…
Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
S. R. Eshwar, Aniruddha Mukherjee, Kintan Saha +4
In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here…
Monotone and Conservative Policy Iteration Beyond the Tabular Case
S. R. Eshwar, Gugan Thoppe, Ananyabrata Barua +2
We introduce Reliable Policy Iteration (RPI) and Conservative RPI (CRPI), variants of Policy Iteration (PI) and Conservative PI (CPI), that retain tabular guarantees under function…
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…
Gradient Boosting Reinforcement Learning
Benjamin Fuhrer, Chen Tessler, Gal Dalal
We present Gradient Boosting Reinforcement Learning (GBRL), a framework that adapts the strengths of gradient boosting trees (GBT) to reinforcement learning (RL) tasks. While neura…
PlaMo: Plan and Move in Rich 3D Physical Environments
Assaf Hallak, Gal Dalal, Chen Tessler +3
Controlling humanoids in complex physically simulated worlds is a long-standing challenge with numerous applications in gaming, simulation, and visual content creation. In our setu…
Tree Search-Based Policy Optimization under Stochastic Execution Delay
David Valensi, Esther Derman, Shie Mannor +1
The standard formulation of Markov decision processes (MDPs) assumes that the agent's decisions are executed immediately. However, in numerous realistic applications such as roboti…
Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
Yihan Du, Anna Winnicki, Gal Dalal +2
Reinforcement Learning from Human Feedback (RLHF) has achieved impressive empirical successes while relying on a small amount of human feedback. However, there is limited theoretic…
On the Products of Stochastic and Diagonal Matrices
Assaf Hallak, Gal Dalal
Consider a stochastic matrix and diagonal matrix In this work, we introduce Tilted matrices. A Tilted matrix is the product , where is a diagonal normalization…
Policy Gradient with Tree Expansion
Gal Dalal, Assaf Hallak, Gugan Thoppe +2
Policy gradient methods are notorious for having a large variance and high sample complexity. To mitigate this, we introduce SoftTreeMax -- a generalization of softmax that employs…
SoftTreeMax: Policy Gradient with Tree Search
Gal Dalal, Assaf Hallak, Shie Mannor +1
Policy-gradient methods are widely used for learning control policies. They can be easily distributed to multiple workers and reach state-of-the-art results in many domains. Unfort…
Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs
Benjamin Fuhrer, Yuval Shpigelman, Chen Tessler +4
As communication protocols evolve, datacenter network utilization increases. As a result, congestion is more frequent, causing higher latency and packet loss. Combined with the inc…
Reinforcement Learning with a Terminator
Guy Tennenholtz, Nadav Merlis, Lior Shani +5
We present the problem of reinforcement learning with exogenous termination. We define the Termination Markov Decision Process (TerMDP), an extension of the MDP framework, in which…
Planning and Learning with Adaptive Lookahead
Aviv Rosenberg, Assaf Hallak, Shie Mannor +2
Some of the most powerful reinforcement learning frameworks use planning for action selection. Interestingly, their planning horizon is either fixed or determined arbitrarily by th…
On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning
Guy Tennenholtz, Assaf Hallak, Gal Dalal +3
We consider the problem of using expert data with unobserved confounders for imitation and reinforcement learning. We begin by defining the problem of learning from confounded expe…
Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction
Assaf Hallak, Gal Dalal, Steven Dalton +3
Tree Search (TS) is crucial to some of the most influential successes in reinforcement learning. Here, we tackle two major challenges with TS that limit its usability: \textit{dist…
Reinforcement Learning for Datacenter Congestion Control
Chen Tessler, Yuval Shpigelman, Gal Dalal +5
We approach the task of network congestion control in datacenters using Reinforcement Learning (RL). Successful congestion control algorithms can dramatically improve latency and o…
Acting in Delayed Environments with Non-Stationary Markov Policies
Esther Derman, Gal Dalal, Shie Mannor
The standard Markov Decision Process (MDP) formulation hinges on the assumption that an action is executed immediately after it was chosen. However, assuming it is often unrealisti…
The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems
Ahmet Inci, Evgeny Bolotin, Yaosheng Fu +4
With deep reinforcement learning (RL) methods achieving results that exceed human capabilities in games, robotics, and simulated environments, continued scaling of RL training is c…
A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound
Gal Dalal, Balazs Szorenyi, Gugan Thoppe
Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as G…
How to Combine Tree-Search Methods in Reinforcement Learning
Yonathan Efroni, Gal Dalal, Bruno Scherrer +1
Finite-horizon lookahead policies are abundantly used in Reinforcement Learning and demonstrate impressive empirical success. Usually, the lookahead policies are implemented with s…
Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning
Yonathan Efroni, Gal Dalal, Bruno Scherrer +1
Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a rec…