{"list":"other","total":53,"rows":[{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1709.07523","title":"Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances","created":"2017-09-21","cited_by_count":201},{"id":"2006.10800","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-06-18","cited_by_count":197},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","cited_by_count":136},{"id":"2011.05869","title":"CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee","created":"2020-11-11","cited_by_count":134},{"id":"1609.07845","title":"Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning","created":"2016-09-26","cited_by_count":118},{"id":"1805.01956","title":"Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning","created":"2018-05-04","cited_by_count":111},{"id":"1906.04005","title":"Safe Reinforcement Learning Using Robust MPC","created":"2019-06-10","cited_by_count":85},{"id":"1709.10082","title":"Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning","created":"2017-09-28","cited_by_count":83},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74},{"id":"1705.10868","title":"Lifelong Multi-Agent Path Finding for Online Pickup and Delivery Tasks","created":"2017-05-30","cited_by_count":64},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61},{"id":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54},{"id":"1906.01202","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","created":"2019-06-04","cited_by_count":44},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35},{"id":"2008.11811","title":"Constrained Markov Decision Processes via Backward Value Functions","created":"2020-08-26","cited_by_count":33},{"id":"2305.14154","title":"Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning","created":"2023-05-23","cited_by_count":24},{"id":"2401.14554","title":"GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control","created":"2024-01-25","cited_by_count":22},{"id":"2001.06627","title":"Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning","created":"2020-01-18","cited_by_count":21},{"id":"1910.12639","title":"MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding","created":"2019-10-25","cited_by_count":20},{"id":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17},{"id":"1909.05150","title":"Online Trajectory Generation with Distributed Model Predictive Control for Multi-Robot Motion Planning","created":"2019-09-11","cited_by_count":14},{"id":"2306.00212","title":"Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning","created":"2023-05-31","cited_by_count":14},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14},{"id":"2311.13714","title":"Learning Safe Control for Multi-Robot Systems: Methods, Verification, and Open Challenges","created":"2023-11-22","cited_by_count":13},{"id":"2304.06281","title":"Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning","created":"2023-04-13","cited_by_count":11},{"id":"2103.12553","title":"Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions","created":"2021-03-23","cited_by_count":10},{"id":"2311.13014","title":"Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control","created":"2023-11-21","cited_by_count":9},{"id":"2502.03640","title":"Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control","created":"2025-02-05","cited_by_count":8},{"id":"2105.12204","title":"Safe Value Functions","created":"2021-05-25","cited_by_count":7},{"id":"1809.04230","title":"Trajectory Generation for Multiagent Point-To-Point Transitions via Distributed Model Predictive Control","created":"2018-09-12","cited_by_count":6},{"id":"2202.10658","title":"Decentralized Safe Multi-agent Stochastic Optimal Control using Deep FBSDEs and ADMM","created":"2022-02-22","cited_by_count":3},{"id":"1911.01832","title":"Distributed Model Predictive Safety Certification for Learning-based Control","created":"2019-11-05","cited_by_count":1},{"id":"2004.01298","title":"Trajectory Optimization for Nonlinear Multi-Agent Systems using Decentralized Learning Model Predictive Control","created":"2020-04-02","cited_by_count":1}],"next_cursor":null}