{"list":"other","total":52,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"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":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"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":"1609.06408","title":"Control Barrier Function Based Quadratic Programs for Safety Critical Systems","created":"2016-09-21","cited_by_count":287},{"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":"2109.06697","title":"Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions","created":"2021-09-14","cited_by_count":94},{"id":"2309.05837","title":"The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems","created":"2023-09-11","cited_by_count":88},{"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":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68},{"id":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54},{"id":"2310.15478","title":"How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systems","created":"2023-10-24","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":"2003.04950","title":"Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach","created":"2020-03-10","cited_by_count":35},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33},{"id":"1903.04706","title":"Control Barrier Functions for Systems with High Relative Degree","created":"2019-03-12","cited_by_count":31},{"id":"1612.01554","title":"Robustness of Control Barrier Functions for Safety Critical Control","created":"2016-12-05","cited_by_count":30},{"id":"2011.04112","title":"Learning Hybrid Control Barrier Functions from Data","created":"2020-11-08","cited_by_count":24},{"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":"2009.01196","title":"Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs","created":"2020-09-02","cited_by_count":22},{"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":"2102.11907","title":"A predictive safety filter for learning-based racing control","created":"2021-02-23","cited_by_count":20},{"id":"2003.11500","title":"Learning Barrier Functions for Constrained Motion Planning with Dynamical Systems","created":"2020-03-25","cited_by_count":17},{"id":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17},{"id":"2111.05969","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","created":"2021-11-10","cited_by_count":16},{"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":"2311.13714","title":"Learning Safe Control for Multi-Robot Systems: Methods, Verification, and Open Challenges","created":"2023-11-22","cited_by_count":13},{"id":"2104.11332","title":"Backup Control Barrier Functions: Formulation and Comparative Study","created":"2021-04-22","cited_by_count":12},{"id":"1903.07823","title":"Safe Policy Synthesis in Multi-Agent POMDPs via Discrete-Time Barrier Functions","created":"2019-03-19","cited_by_count":11},{"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":"2105.12204","title":"Safe Value Functions","created":"2021-05-25","cited_by_count":7},{"id":"2003.07819","title":"Control Barrier Function based Quadratic Programs Introduce Undesirable Asymptotically Stable Equilibria","created":"2020-03-17","cited_by_count":3},{"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":"2405.11391","title":"Optimal control barrier functions for RL based safe powertrain control","created":"2024-05-18","cited_by_count":3},{"id":"2207.04915","title":"Multi-agent systems with CBF-based controllers -- collision avoidance and liveness from instability","created":"2022-07-11","cited_by_count":2},{"id":"2409.09573","title":"Decentralized Safe and Scalable Multi-Agent Control under Limited Actuation","created":"2024-09-15","cited_by_count":1}],"next_cursor":null}