3 citations · 6 across the 12 of their papers we have counts for
14 papers
BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
Ankur Samanta, Akshayaa Magesh, Tal Lancewicki +7
Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environm…
Online Learning in MDPs with Partially Adversarial Transitions and Losses
Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour
We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of steps per episode. This model ca…
Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
Ofir Schlisselberg, Tal Lancewicki, Peter Auer +1
We study the multi-armed bandit problem with adversarially chosen delays in the Best-of-Both-Worlds (BoBW) framework, which aims to achieve near-optimal performance in both stochas…
Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
Tal Lancewicki, Yishay Mansour
We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent…
Individual Regret in Cooperative Stochastic Multi-Armed Bandits
Idan Barnea, Tal Lancewicki, Yishay Mansour
We study the regret in stochastic Multi-Armed Bandits (MAB) with multiple agents that communicate over an arbitrary connected communication graph. We analyzed a variant of Cooperat…
Delay as Payoff in MAB
Ofir Schlisselberg, Ido Cohen, Tal Lancewicki +1
In this paper, we investigate a variant of the classical stochastic Multi-armed Bandit (MAB) problem, where the payoff received by an agent (either cost or reward) is both delayed,…
Towards Natural Language-Driven Assembly Using Foundation Models
Omkar Joglekar, Tal Lancewicki, Shir Kozlovsky +3
Large Language Models (LLMs) and strong vision models have enabled rapid research and development in the field of Vision-Language-Action models that enable robotic control. The mai…
A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs
Dirk van der Hoeven, Lukas Zierahn, Tal Lancewicki +2
We derive a new analysis of Follow The Regularized Leader (FTRL) for online learning with delayed bandit feedback. By separating the cost of delayed feedback from that of bandit fe…
Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback
Tal Lancewicki, Aviv Rosenberg, Dmitry Sotnikov
Policy Optimization (PO) is one of the most popular methods in Reinforcement Learning (RL). Thus, theoretical guarantees for PO algorithms have become especially important to the R…
Regret Minimization and Convergence to Equilibria in General-sum Markov Games
Liad Erez, Tal Lancewicki, Uri Sherman +2
An abundance of recent impossibility results establish that regret minimization in Markov games with adversarial opponents is both statistically and computationally intractable. Ne…
Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback
Tiancheng Jin, Tal Lancewicki, Haipeng Luo +2
The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately. However, in practice feedback is often observed in delay. This…
Cooperative Online Learning in Stochastic and Adversarial MDPs
Tal Lancewicki, Aviv Rosenberg, Yishay Mansour
We study cooperative online learning in stochastic and adversarial Markov decision process (MDP). That is, in each episode, agents interact with an MDP simultaneously and share…
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Tal Lancewicki, Shahar Segal, Tomer Koren +1
We study the stochastic Multi-Armed Bandit (MAB) problem with random delays in the feedback received by the algorithm. We consider two settings: the reward-dependent delay setting,…
Learning Adversarial Markov Decision Processes with Delayed Feedback
Tal Lancewicki, Aviv Rosenberg, Yishay Mansour
Reinforcement learning typically assumes that agents observe feedback for their actions immediately, but in many real-world applications (like recommendation systems) feedback is o…