{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"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":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"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":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1901.10031","title":"Lyapunov-based Safe Policy Optimization for Continuous Control","created":"2019-01-28","cited_by_count":145},{"id":"1910.09615","title":"IPO: Interior-point Policy Optimization under Constraints","created":"2019-10-21","cited_by_count":132},{"id":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74},{"id":"1710.05465","title":"Flow: A Modular Learning Framework for Mixed Autonomy Traffic","created":"2017-10-16","cited_by_count":73},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60},{"id":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59},{"id":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59},{"id":"1709.04571","title":"When Waiting is not an Option : Learning Options with a Deliberation Cost","created":"2017-09-14","cited_by_count":58},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54},{"id":"2104.02808","title":"Robust Control Barrier-Value Functions for Safety-Critical Control","created":"2021-04-06","cited_by_count":51},{"id":"1809.10330","title":"Variance reduction properties of the reparameterization trick","created":"2018-09-27","cited_by_count":41},{"id":"1910.04450","title":"Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards","created":"2019-10-10","cited_by_count":40},{"id":"2205.01758","title":"Differentiable Simulation of Soft Multi-body Systems","created":"2022-05-03","cited_by_count":39},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37},{"id":"1901.08492","title":"Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning","created":"2019-01-24","cited_by_count":33},{"id":"2110.13827","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","created":"2021-10-26","cited_by_count":33},{"id":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30},{"id":"2409.18031","title":"Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving","created":"2024-09-26","cited_by_count":27},{"id":"2009.01196","title":"Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs","created":"2020-09-02","cited_by_count":22},{"id":"2110.07246","title":"HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism","created":"2021-10-14","cited_by_count":19},{"id":"2011.12719","title":"RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem","created":"2020-11-25","cited_by_count":16},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14},{"id":"1912.09957","title":"Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates","created":"2019-12-20","cited_by_count":13},{"id":"2209.09640","title":"Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":13},{"id":"1602.03351","title":"Adaptive Skills, Adaptive Partitions (ASAP)","created":"2016-02-10","cited_by_count":11},{"id":"2211.17250","title":"Safe and Efficient Reinforcement Learning Using Disturbance-Observer-Based Control Barrier Functions","created":"2022-11-30","cited_by_count":11},{"id":"2303.04313","title":"Online Control Barrier Functions for Decentralized Multi-Agent Navigation","created":"2023-03-08","cited_by_count":11},{"id":"2502.03640","title":"Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control","created":"2025-02-05","cited_by_count":8},{"id":"2403.17338","title":"Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems","created":"2024-03-26","cited_by_count":7},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6},{"id":"2401.13231","title":"DittoGym: Learning to Control Soft Shape-Shifting Robots","created":"2024-01-24","cited_by_count":6},{"id":"2504.15425","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","created":"2025-04-21","cited_by_count":6},{"id":"2309.10657","title":"Learning Adaptive Safety for Multi-Agent Systems","created":"2023-09-19","cited_by_count":3},{"id":"1911.04096","title":"UW-MARL: Multi-Agent Reinforcement Learning for Underwater Adaptive Sampling using Autonomous Vehicles","created":"2019-11-11","cited_by_count":2}],"next_cursor":null}