{"total":12,"rows":[{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2404.18909","title":"Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty","created":"2024-04-29","cited_by_count":25,"area":null},{"id":"2205.14572","title":"No-regret Learning in Repeated First-Price Auctions with Budget Constraints","created":"2022-05-29","cited_by_count":9,"area":null},{"id":"2302.14004","title":"Optimistic Planning by Regularized Dynamic Programming","created":"2023-02-27","cited_by_count":8,"area":null},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2107.00685","title":"Gap-Dependent Bounds for Two-Player Markov Games","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2502.14043","title":"Safe Learning Under Irreversible Dynamics via Asking for Help","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2405.08253","title":"Thompson Sampling for Infinite-Horizon Discounted Decision Processes","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2408.08934","title":"A Factored MDP Approach To Moving Target Defense With Dynamic Threat Modeling and Cost Efficiency","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2508.10804","title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","created":"2025-08-14","cited_by_count":0,"area":null}],"next_cursor":null}