Skip to content
conftrace_

bellman eluder dimension

5 papers

Explore in graph

Also known as

BE DIMENSION

Co-occurring keywords · papers mentioning both

function approximation (4) sample complexity (3) optimal policy (2) reinforcement learning (2) myopic exploration (1) zero-sum markov game (1) actor critic (1) structural assumption (1) optimization-based algorithm (1) strategic exploration (1)

Papers

Actor-Critics Can Achieve Optimal Sample Efficiency ICML 2025 Non-stationary Reinforcement Learning under General Function Approximation ICML 2023 Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation ICML 2022 The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces ICML 2022 Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms NeurIPS 2021