{"total":27,"rows":[{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186,"area":null},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153,"area":null},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35,"area":null},{"id":"2109.12286","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","created":"2021-09-25","cited_by_count":19,"area":null},{"id":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19,"area":null},{"id":"2312.04103","title":"Enhancing the Rationale-Input Alignment for Self-explaining Rationalization","created":"2023-12-07","cited_by_count":15,"area":null},{"id":"2209.12713","title":"Multi-Agent Coordination via Multi-Level Communication","created":"2022-09-26","cited_by_count":14,"area":null},{"id":"2305.13599","title":"Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2308.07536","title":"Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem","created":"2023-08-15","cited_by_count":13,"area":null},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2406.12771","title":"First-Order Methods for Linearly Constrained Bilevel Optimization","created":"2024-06-18","cited_by_count":10,"area":null},{"id":"2405.18209","title":"Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2110.11721","title":"Projection-Free Algorithm for Stochastic Bi-level Optimization","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2207.13283","title":"INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks","created":"2022-07-27","cited_by_count":8,"area":null},{"id":"2212.02376","title":"DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization","created":"2022-12-05","cited_by_count":7,"area":null},{"id":"2404.00158","title":"Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing","created":"2024-03-29","cited_by_count":6,"area":null},{"id":"2209.08244","title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","created":"2022-09-17","cited_by_count":5,"area":null},{"id":"2304.10351","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2306.06236","title":"iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2211.04088","title":"A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2206.05733","title":"Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic","created":"2022-06-12","cited_by_count":1,"area":null},{"id":"2606.21153","title":"DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity","created":"2026-06-19","cited_by_count":1,"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":"2412.03072","title":"Preference-based opponent shaping in differentiable games","created":"2024-12-04","cited_by_count":0,"area":null}],"next_cursor":null}