{"total":318,"rows":[{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410,"area":null},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56,"area":null},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40,"area":null},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39,"area":null},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2206.10607","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","created":"2022-06-20","cited_by_count":34,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2201.04735","title":"Planning in Observable POMDPs in Quasipolynomial Time","created":"2022-01-12","cited_by_count":25,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2210.14876","title":"Quantum deep recurrent reinforcement learning","created":"2022-10-26","cited_by_count":24,"area":null},{"id":"2111.03941","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","created":"2021-11-06","cited_by_count":23,"area":null},{"id":"2206.09674","title":"EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL","created":"2022-06-20","cited_by_count":23,"area":null},{"id":"2505.05522","title":"Continuous Thought Machines","created":"2025-05-08","cited_by_count":22,"area":null},{"id":"2110.12628","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","cited_by_count":21,"area":null},{"id":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2107.03635","title":"Sublinear Regret for Learning POMDPs","created":"2021-07-08","cited_by_count":19,"area":null},{"id":"2110.07246","title":"HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism","created":"2021-10-14","cited_by_count":19,"area":null},{"id":"2202.00104","title":"Generalization in Cooperative Multi-Agent Systems","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2210.04839","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2305.19044","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","created":"2023-05-30","cited_by_count":19,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2110.15949","title":"Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains","created":"2021-10-29","cited_by_count":18,"area":null},{"id":"2209.10113","title":"Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":18,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"area":null},{"id":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2205.02589","title":"A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning","created":"2022-05-05","cited_by_count":16,"area":null},{"id":"2205.11051","title":"Flow-based Recurrent Belief State Learning for POMDPs","created":"2022-05-23","cited_by_count":16,"area":null},{"id":"2205.13476","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","created":"2022-05-26","cited_by_count":16,"area":null},{"id":"2309.17207","title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2101.04237","title":"Solving Common-Payoff Games with Approximate Policy Iteration","created":"2021-01-11","cited_by_count":15,"area":null},{"id":"2212.12735","title":"An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context","created":"2022-12-24","cited_by_count":15,"area":null},{"id":"2111.02104","title":"Model-Based Episodic Memory Induces Dynamic Hybrid Controls","created":"2021-11-03","cited_by_count":14,"area":null},{"id":"2308.16316","title":"Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art","created":"2023-08-30","cited_by_count":14,"area":null},{"id":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2312.01624","title":"GVFs in the Real World: Making Predictions Online for Water Treatment","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2107.06434","title":"Centralized Model and Exploration Policy for Multi-Agent RL","created":"2021-07-14","cited_by_count":12,"area":null},{"id":"2208.03520","title":"Recurrent networks, hidden states and beliefs in partially observable environments","created":"2022-08-06","cited_by_count":12,"area":null},{"id":"2210.05448","title":"A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2209.07225","title":"MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2306.06766","title":"Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning","created":"2023-06-11","cited_by_count":11,"area":null},{"id":"2412.15619","title":"Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning","created":"2024-12-20","cited_by_count":11,"area":null},{"id":"2104.11106","title":"Formula RL: Deep Reinforcement Learning for Autonomous Racing using Telemetry Data","created":"2021-04-22","cited_by_count":10,"area":null},{"id":"2106.09086","title":"Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings","created":"2021-06-16","cited_by_count":10,"area":null},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2205.11104","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2406.04089","title":"On Limitation of Transformer for Learning HMMs","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2108.09141","title":"Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation","created":"2021-08-20","cited_by_count":9,"area":null},{"id":"2202.06557","title":"Reinforcement Learning in Presence of Discrete Markovian Context Evolution","created":"2022-02-14","cited_by_count":9,"area":null},{"id":"2303.03284","title":"The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2310.04128","title":"Reinforcement Learning with Fast and Forgetful Memory","created":"2023-10-06","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":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2110.00121","title":"Emergence of Theory of Mind Collaboration in Multiagent Systems","created":"2021-09-30","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2603.00730","title":"MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning","created":"2026-02-28","cited_by_count":8,"area":null},{"id":"2105.06228","title":"SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2106.09274","title":"Cooperative Multi-Agent Reinforcement Learning Based Distributed Dynamic Spectrum Access in Cognitive Radio Networks","created":"2021-06-17","cited_by_count":7,"area":null},{"id":"2201.11994","title":"FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2305.05586","title":"RLocator: Reinforcement Learning for Bug Localization","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2309.14078","title":"ODE-based Recurrent Model-free Reinforcement Learning for POMDPs","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2310.02435","title":"Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2109.07752","title":"Deep Visual Navigation under Partial Observability","created":"2021-09-16","cited_by_count":6,"area":null},{"id":"2203.04806","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2206.14048","title":"Short-Term Plasticity Neurons Learning to Learn and Forget","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","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":"2504.15425","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2510.07151","title":"ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems","created":"2025-10-08","cited_by_count":6,"area":null}],"next_cursor":"100"}