{"list":"other","total":60,"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"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":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"1704.04394","title":"DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents","created":"2017-04-14","cited_by_count":310},{"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":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"1805.06771","title":"Convolutional Social Pooling for Vehicle Trajectory Prediction","created":"2018-05-15","cited_by_count":221},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1710.04689","title":"Social Attention: Modeling Attention in Human Crowds","created":"2017-10-12","cited_by_count":186},{"id":"1905.01296","title":"PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings","created":"2019-05-03","cited_by_count":179},{"id":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100},{"id":"1609.05559","title":"Opponent Modeling in Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":97},{"id":"2011.06619","title":"Learning Latent Representations to Influence Multi-Agent Interaction","created":"2020-11-12","cited_by_count":93},{"id":"1812.04767","title":"TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions","created":"2018-12-12","cited_by_count":82},{"id":"1911.10715","title":"Multi-Agent Game Abstraction via Graph Attention Neural Network","created":"2019-11-25","cited_by_count":82},{"id":"1308.3513","title":"Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations","created":"2013-08-15","cited_by_count":70},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58},{"id":"2006.09447","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning","created":"2020-06-16","cited_by_count":57},{"id":"1905.02680","title":"Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving","created":"2019-05-06","cited_by_count":52},{"id":"2010.00581","title":"Emergent Social Learning via Multi-agent Reinforcement Learning","created":"2020-10-01","cited_by_count":44},{"id":"2212.08710","title":"JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving","created":"2022-12-16","cited_by_count":40},{"id":"1909.03510","title":"Bi-level Actor-Critic for Multi-agent Coordination","created":"2019-09-08","cited_by_count":39},{"id":"1912.01118","title":"Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs","created":"2019-12-02","cited_by_count":34},{"id":"2206.14116","title":"SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving","created":"2022-06-28","cited_by_count":32},{"id":"2110.08229","title":"Influencing Towards Stable Multi-Agent Interactions","created":"2021-10-05","cited_by_count":24},{"id":"2005.05441","title":"Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments","created":"2020-05-11","cited_by_count":22},{"id":"1712.03913","title":"A Non-Cooperative Game Approach to Autonomous Racing","created":"2017-12-11","cited_by_count":19},{"id":"2003.04424","title":"CMetric: A Driving Behavior Measure Using Centrality Functions","created":"2020-03-09","cited_by_count":19},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18},{"id":"1907.08752","title":"RobustTP: End-to-End Trajectory Prediction for Heterogeneous Road-Agents in Dense Traffic with Noisy Sensor Inputs","created":"2019-07-20","cited_by_count":16},{"id":"2011.03748","title":"B-GAP: Behavior-Rich Simulation and Navigation for Autonomous Driving","created":"2020-11-07","cited_by_count":15},{"id":"2008.04452","title":"Multi-Agent Safe Planning with Gaussian Processes","created":"2020-08-10","cited_by_count":13},{"id":"1803.02018","title":"Intent-aware Multi-agent Reinforcement Learning","created":"2018-03-06","cited_by_count":12},{"id":"2109.07648","title":"METEOR:A Dense, Heterogeneous, and Unstructured Traffic Dataset With Rare Behaviors","created":"2021-09-16","cited_by_count":12},{"id":"2111.02964","title":"Using Graph-Theoretic Machine Learning to Predict Human Driver Behavior","created":"2021-11-04","cited_by_count":12},{"id":"2207.12380","title":"Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles","created":"2022-07-25","cited_by_count":11},{"id":"2302.10238","title":"Multiagent Inverse Reinforcement Learning via Theory of Mind Reasoning","created":"2023-02-20","cited_by_count":11},{"id":"1910.07613","title":"Learning from My Partner's Actions: Roles in Decentralized Robot Teams","created":"2019-10-16","cited_by_count":10},{"id":"1910.00049","title":"GraphRQI: Classifying Driver Behaviors Using Graph Spectrums","created":"2019-09-30","cited_by_count":9},{"id":"2203.04421","title":"Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction","created":"2022-03-08","cited_by_count":9},{"id":"2203.12705","title":"RILI: Robustly Influencing Latent Intent","created":"2022-03-23","cited_by_count":8},{"id":"2210.08390","title":"SOCIALMAPF: Optimal and Efficient Multi-Agent Path Finding with Strategic Agents for Social Navigation","created":"2022-10-15","cited_by_count":6},{"id":"1803.00881","title":"Identifying Driver Behaviors using Trajectory Features for Vehicle Navigation","created":"2018-03-02","cited_by_count":5},{"id":"2206.00233","title":"DM$^2$: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching","created":"2022-06-01","cited_by_count":5},{"id":"1908.09031","title":"Generic Tracking and Probabilistic Prediction Framework and Its Application in Autonomous Driving","created":"2019-08-23","cited_by_count":4},{"id":"2206.01488","title":"GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving","created":"2022-06-03","cited_by_count":3}],"next_cursor":null}