{"total":98,"rows":[{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251,"area":null},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132,"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":"2110.01219","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","created":"2021-10-04","cited_by_count":68,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"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":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"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":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2201.12569","title":"Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes","created":"2022-01-29","cited_by_count":23,"area":null},{"id":"2301.03220","title":"Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks","created":"2023-01-09","cited_by_count":21,"area":null},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18,"area":null},{"id":"2211.01991","title":"Leveraging Fully Observable Policies for Learning under Partial Observability","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2212.07313","title":"Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems","created":"2022-12-14","cited_by_count":18,"area":null},{"id":"2110.01388","title":"Neural Network Verification in Control","created":"2021-09-30","cited_by_count":14,"area":null},{"id":"2209.10081","title":"Revisiting Discrete Soft Actor-Critic","created":"2022-09-21","cited_by_count":13,"area":null},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2310.03912","title":"RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2112.02852","title":"Target Entropy Annealing for Discrete Soft Actor-Critic","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2103.02287","title":"Addressing Action Oscillations through Learning Policy Inertia","created":"2021-03-03","cited_by_count":9,"area":null},{"id":"2105.00990","title":"Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials","created":"2021-05-03","cited_by_count":8,"area":null},{"id":"2312.08884","title":"Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems","created":"2023-12-14","cited_by_count":8,"area":null},{"id":"2303.17615","title":"Utilizing Reinforcement Learning for de novo Drug Design","created":"2023-03-30","cited_by_count":7,"area":null},{"id":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2108.13525","title":"Identifying optimal cycles in quantum thermal machines with reinforcement-learning","created":"2021-08-30","cited_by_count":6,"area":null},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2402.15402","title":"Grasp, See, and Place: Efficient Unknown Object Rearrangement with Policy Structure Prior","created":"2024-02-23","cited_by_count":5,"area":null},{"id":"2404.11014","title":"Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs","created":"2024-04-17","cited_by_count":5,"area":null},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2112.03636","title":"Godot Reinforcement Learning Agents","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2207.03081","title":"DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":null},{"id":"2208.14501","title":"Model-Based Reinforcement Learning with SINDy","created":"2022-08-30","cited_by_count":4,"area":null},{"id":"2212.02075","title":"Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks","created":"2022-12-05","cited_by_count":4,"area":null},{"id":"2308.04834","title":"View while Moving: Efficient Video Recognition in Long-untrimmed Videos","created":"2023-08-09","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":"2308.13270","title":"A Game of Bundle Adjustment -- Learning Efficient Convergence","created":"2023-08-25","cited_by_count":4,"area":null},{"id":"2402.02186","title":"Evolution Guided Generative Flow Networks","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2103.11823","title":"Self-Organizing mmWave MIMO Cell-Free Networks With Hybrid Beamforming: A Hierarchical DRL-Based Design","created":"2021-03-17","cited_by_count":3,"area":null},{"id":"2109.08512","title":"Soft Actor-Critic With Integer Actions","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2109.11867","title":"The $f$-Divergence Reinforcement Learning Framework","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2303.04356","title":"Soft Actor-Critic Algorithm with Truly-satisfied Inequality Constraint","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2308.05318","title":"RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation","created":"2023-08-10","cited_by_count":3,"area":null},{"id":"2309.04459","title":"Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2404.06975","title":"Multi-Agent Soft Actor-Critic with Coordinated Loss for Autonomous Mobility-on-Demand Fleet Control","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2503.09423","title":"Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2102.00168","title":"Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm","created":"2021-01-30","cited_by_count":2,"area":null},{"id":"2201.11727","title":"Multi-Agent Reinforcement Learning for Network Load Balancing in Data Center","created":"2022-01-27","cited_by_count":2,"area":null},{"id":"2203.04927","title":"Investigation of Factorized Optical Flows as Mid-Level Representations","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2211.13260","title":"Actively Learning Costly Reward Functions for Reinforcement Learning","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2302.10720","title":"Learning to Play Text-based Adventure Games with Maximum Entropy Reinforcement Learning","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2302.13036","title":"Limited Query Graph Connectivity Test","created":"2023-02-25","cited_by_count":2,"area":null},{"id":"2305.01519","title":"BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2102.11403","title":"Exploring Supervised and Unsupervised Rewards in Machine Translation","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2111.14204","title":"Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2204.04785","title":"Model-free optimization of power/efficiency tradeoffs in quantum thermal machines using reinforcement learning","created":"2022-04-10","cited_by_count":1,"area":null},{"id":"2211.05346","title":"RARE: Renewable Energy Aware Resource Management in Datacenters","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2303.02731","title":"Virtual Guidance as a Mid-level Representation for Navigation with Augmented Reality","created":"2023-03-05","cited_by_count":1,"area":null},{"id":"2308.10203","title":"Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2308.16210","title":"Deep Inductive Logic Programming meets Reinforcement Learning","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2309.03758","title":"Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2310.03687","title":"Probabilistic Generative Modeling for Procedural Roundabout Generation for Developing Countries","created":"2023-10-05","cited_by_count":1,"area":null},{"id":"2310.07724","title":"Visual Forecasting as a Mid-level Representation for Avoidance","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2402.09113","title":"How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2408.15328","title":"Artificially intelligent Maxwell's demon for optimal control of open quantum systems","created":"2024-08-27","cited_by_count":1,"area":null},{"id":"2411.07200","title":"'Explaining RL Decisions with Trajectories': A Reproducibility Study","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2506.18627","title":"Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2511.15002","title":"Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2101.11188","title":"GymD2D: A Device-to-Device Underlay Cellular Offload Evaluation Platform","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2103.16732","title":"Simultaneous Navigation and Construction Benchmarking Environments","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2109.09037","title":"Dual Behavior Regularized Reinforcement Learning","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2201.02968","title":"An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic","created":"2022-01-09","cited_by_count":0,"area":null},{"id":"2205.15656","title":"Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems","created":"2022-05-31","cited_by_count":0,"area":null},{"id":"2206.05108","title":"Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropy","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2206.06712","title":"Visual Radial Basis Q-Network","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2208.14447","title":"A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Space","created":"2022-08-30","cited_by_count":0,"area":null},{"id":"2209.00372","title":"Sample Efficient Learning of Factored Embeddings of Tensor Fields","created":"2022-09-01","cited_by_count":0,"area":null},{"id":"2209.14781","title":"Learning Parsimonious Dynamics for Generalization in Reinforcement Learning","created":"2022-09-29","cited_by_count":0,"area":null},{"id":"2211.13070","title":"Enhancing team performance with transfer-learning during real-world human-robot collaboration","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2307.02345","title":"LLQL: Logistic Likelihood Q-Learning for Reinforcement Learning","created":"2023-07-05","cited_by_count":0,"area":null},{"id":"2308.14652","title":"Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Arm","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2310.02605","title":"Multi-Agent Reinforcement Learning for Power Grid Topology Optimization","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2310.08660","title":"Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2310.17173","title":"DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2311.10406","title":"Decentralized Energy Marketplace via NFTs and AI-based Agents","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2403.15834","title":"ARO: Large Language Model Supervised Robotics Text2Skill Autonomous Learning","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2505.01028","title":"Adaptive Wizard for Removing Cross-Tier Misconfigurations in Active Directory","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.01966","title":"A Goal-Oriented Reinforcement Learning-Based Path Planning Algorithm for Modular Self-Reconfigurable Satellites","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2508.13532","title":"MuFlex: A Scalable, Physics-based Platform for Multi-Building Flexibility Analysis and Coordination","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2602.17375","title":"MDP Planning as Policy Inference","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.19322","title":"A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.25394","title":"FactorLibrary: From Polynomials to Circuits via Recursive Subgoals","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.30072","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.22009","title":"Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.05936","title":"Combining Improvements in Uplink AI-RAN","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}