Shie Mannor

Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models

Spectral Bellman Method: Unifying Representation and Exploration in RL

Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models

Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces

Representative Action Selection for Large Action Space Meta-Bandits

Hierarchical Bandits for Adversarial Online Configuration Optimization

State Entropy Regularization for Robust Reinforcement Learning

Efficient Fairness-Performance Pareto Front Computation

On the Convergence of Single-Timescale Actor-Critic

On Bits and Bandits: Quantifying the Regret-Information Trade-off

Global Convergence of Policy Gradient in Average Reward MDPs

Non-rectangular Robust MDPs with Normed Uncertainty Sets

Reinforcement Learning with Segment Feedback

Policy Gradient with Tree Expansion

Learning Multiple Initial Solutions to Optimization Problems

Efficient Fairness-Performance Pareto Front Computation

Reinforcement Learning with Segment Feedback

Policy Optimized Text-to-Image Pipeline Design

Learning Multiple Initial Solutions to Optimization Problems

A Classification View on Meta Learning Bandits

Policy Gradient with Tree Expansion

Uncovering Untapped Potential in Sample-Efficient World Model Agents

Real Time Macro-Block Rate Control for Task-Aware Video Compression Using Reinforcement Learning

Improved Sample Complexity for Global Convergence of Actor-Critic Algorithms

Human-like Communication Strategies for Improved Multi-Agent Reinforcement Learning

SQT -- rough conservative actor critic