{"total":12,"rows":[{"id":"2202.04129","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence","created":"2022-02-08","cited_by_count":57,"area":null},{"id":"2301.11518","title":"Online Learning in Stackelberg Games with an Omniscient Follower","created":"2023-01-27","cited_by_count":15,"area":null},{"id":"2401.15240","title":"Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games","created":"2024-01-26","cited_by_count":13,"area":null},{"id":"2311.06210","title":"Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication","created":"2023-11-10","cited_by_count":8,"area":null},{"id":"2401.10949","title":"The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2403.00188","title":"Impact of Decentralized Learning on Player Utilities in Stackelberg Games","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2503.08961","title":"Multiplayer Information Asymmetric Contextual Bandits","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2211.15792","title":"Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2405.03158","title":"Decentralized Online Learning in General-Sum Stackelberg Games","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2405.06689","title":"Policy Iteration for Two-Player General-Sum Stochastic Stackelberg Games","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2512.10952","title":"Hierarchical Dataset Selection for High-Quality Data Sharing","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.00952","title":"Optimal Budgeted Adaptation of Large Language Models","created":"2026-02-01","cited_by_count":0,"area":null}],"next_cursor":null}