{"total":187,"rows":[{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2204.05306","title":"Full-Spectrum Out-of-Distribution Detection","created":"2022-04-11","cited_by_count":63,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2106.02748","title":"Decentralized Q-Learning in Zero-sum Markov Games","created":"2021-06-04","cited_by_count":58,"area":null},{"id":"2107.07630","title":"Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi","created":"2021-07-15","cited_by_count":40,"area":null},{"id":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"area":null},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32,"area":null},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29,"area":null},{"id":"2112.01280","title":"Learning Graphon Mean Field Games and Approximate Nash Equilibria","created":"2021-11-29","cited_by_count":28,"area":null},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"area":null},{"id":"2104.00742","title":"Confidence Calibration for Domain Generalization under Covariate Shift","created":"2021-04-01","cited_by_count":27,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2405.19946","title":"Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf","created":"2024-05-30","cited_by_count":24,"area":null},{"id":"2106.07551","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","created":"2021-06-05","cited_by_count":23,"area":null},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23,"area":null},{"id":"2206.12301","title":"On the Limitations of Elo: Real-World Games, are Transitive, not Additive","created":"2022-06-21","cited_by_count":23,"area":null},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23,"area":null},{"id":"2110.04041","title":"Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity","created":"2021-10-08","cited_by_count":22,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"area":null},{"id":"2102.09812","title":"Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space","created":"2021-02-19","cited_by_count":20,"area":null},{"id":"2105.13807","title":"Gym-$\\mu$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning","created":"2021-05-21","cited_by_count":19,"area":null},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2202.03634","title":"Multi-Agent Path Finding with Prioritized Communication Learning","created":"2022-02-08","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2203.11203","title":"Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach","created":"2022-03-19","cited_by_count":17,"area":null},{"id":"2211.03481","title":"Predictive Coding beyond Gaussian Distributions","created":"2022-11-07","cited_by_count":16,"area":null},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2106.15587","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2201.08484","title":"Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming","created":"2022-01-20","cited_by_count":14,"area":null},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2209.11553","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","created":"2022-09-23","cited_by_count":14,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2201.08278","title":"Lifelong Learning Metrics","created":"2022-01-20","cited_by_count":13,"area":null},{"id":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2301.07799","title":"A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems","created":"2023-01-18","cited_by_count":13,"area":null},{"id":"2106.00517","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","created":"2021-06-01","cited_by_count":12,"area":null},{"id":"2206.04860","title":"Conformal Prediction Intervals for Markov Decision Process Trajectories","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2208.04957","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","created":"2022-08-09","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2402.01786","title":"COA-GPT: Generative Pre-trained Transformers for Accelerated Course of Action Development in Military Operations","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2106.05506","title":"Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program","created":"2021-06-10","cited_by_count":11,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2208.05056","title":"Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2","created":"2022-08-09","cited_by_count":11,"area":null},{"id":"2408.00170","title":"CREW: Facilitating Human-AI Teaming Research","created":"2024-07-31","cited_by_count":11,"area":null},{"id":"2104.06890","title":"An Introduction of mini-AlphaStar","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","cited_by_count":10,"area":null},{"id":"2210.03022","title":"Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning","created":"2022-10-04","cited_by_count":10,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2307.09470","title":"Multi-Player Zero-Sum Markov Games with Networked Separable Interactions","created":"2023-07-13","cited_by_count":10,"area":null},{"id":"2404.17794","title":"GPT for Games: A Scoping Review (2020-2023)","created":"2024-04-27","cited_by_count":10,"area":null},{"id":"2411.00308","title":"GPT for Games: An Updated Scoping Review (2020-2024)","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2109.12508","title":"LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates","created":"2021-09-26","cited_by_count":9,"area":null},{"id":"2301.05334","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","created":"2023-01-13","cited_by_count":9,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2306.11551","title":"IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2105.04758","title":"Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2203.06416","title":"Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems","created":"2022-03-12","cited_by_count":7,"area":null},{"id":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2404.12824","title":"MAexp: A Generic Platform for RL-based Multi-Agent Exploration","created":"2024-04-19","cited_by_count":7,"area":null},{"id":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2104.07294","title":"Generalising Discrete Action Spaces with Conditional Action Trees","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2106.10365","title":"Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2112.00800","title":"Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text","created":"2021-12-01","cited_by_count":6,"area":null},{"id":"2203.10941","title":"Transfer Dynamics in Emergent Evolutionary Curricula","created":"2022-03-03","cited_by_count":6,"area":null},{"id":"2305.05566","title":"SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2312.06258","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2408.09135","title":"Vanilla Gradient Descent for Oblique Decision Trees","created":"2024-08-17","cited_by_count":6,"area":null},{"id":"2410.16024","title":"SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2105.06351","title":"Convergence and Implicit Bias of Gradient Flow on Overparametrized Linear Networks","created":"2021-05-13","cited_by_count":5,"area":null},{"id":"2111.12600","title":"Learning State Representations via Retracing in Reinforcement Learning","created":"2021-11-24","cited_by_count":5,"area":null},{"id":"2203.16777","title":"Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2208.07298","title":"Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraft","created":"2022-08-15","cited_by_count":5,"area":null},{"id":"2303.05584","title":"SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces","created":"2023-03-09","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":"2306.10486","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","created":"2023-06-18","cited_by_count":5,"area":null},{"id":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2102.06782","title":"Q-Value Weighted Regression: Reinforcement Learning with Limited Data","created":"2021-02-12","cited_by_count":4,"area":null},{"id":"2207.10218","title":"The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learning","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2308.04958","title":"Improving Autonomous Separation Assurance through Distributed Reinforcement Learning with Attention Networks","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2308.06668","title":"Large Language Models and Foundation Models in Smart Agriculture: Basics, Opportunities, and Challenges","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2502.11122","title":"Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2502.13388","title":"Reflection of Episodes: Learning to Play Game from Expert and Self Experiences","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2607.06701","title":"SPEAR: A Simulator for Photorealistic Embodied AI Research","created":"2026-07-07","cited_by_count":4,"area":null},{"id":"2102.12307","title":"Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2105.10211","title":"Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games","created":"2021-05-21","cited_by_count":3,"area":null}],"next_cursor":"100"}