{"total":22,"rows":[{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2405.12952","title":"Truncated Variance Reduced Value Iteration","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2307.06877","title":"The complexity of non-stationary reinforcement learning","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2301.12802","title":"Planning Multiple Epidemic Interventions with Reinforcement Learning","created":"2023-01-30","cited_by_count":5,"area":null},{"id":"2210.08740","title":"Risk-Sensitive Markov Decision Processes with Long-Run CVaR Criterion","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2206.05809","title":"Geometric Policy Iteration for Markov Decision Processes","created":"2022-06-12","cited_by_count":3,"area":null},{"id":"2302.11761","title":"Intermittently Observable Markov Decision Processes","created":"2023-02-23","cited_by_count":3,"area":null},{"id":"2312.04216","title":"CODEX: A Cluster-Based Method for Explainable Reinforcement Learning","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2207.01613","title":"Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2505.00795","title":"Howard's Policy Iteration is Subexponential for Deterministic Markov Decision Problems with Rewards of Fixed Bit-size and Arbitrary Discount Factor","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2111.03699","title":"A space of goals: the cognitive geometry of informationally bounded agents","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2210.01766","title":"Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2302.13115","title":"Dual Formulation for Chance Constrained Stochastic Shortest Path with Application to Autonomous Vehicle Behavior Planning","created":"2023-02-25","cited_by_count":1,"area":null},{"id":"2305.00410","title":"Indexability of Finite State Restless Multi-Armed Bandit and Rollout Policy","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2407.14092","title":"Integrated Push-and-Pull Update Model for Goal-Oriented Effective Communication","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2503.06725","title":"Pull-Based Query Scheduling for Goal-Oriented Semantic Communication","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2503.22779","title":"Policy Optimization and Multi-agent Reinforcement Learning for Mean-variance Team Stochastic Games","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2508.01129","title":"Human-Robot Red Teaming for Safety-Aware Reasoning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2512.15824","title":"State-Augmented Graphs for Circular Economy Triage","created":"2025-12-17","cited_by_count":0,"area":null}],"next_cursor":null}