{"total":68,"rows":[{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2308.07200","title":"Neural Categorical Priors for Physics-Based Character Control","created":"2023-08-14","cited_by_count":38,"area":null},{"id":"2310.11731","title":"Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning","created":"2023-10-18","cited_by_count":36,"area":"offlinerl"},{"id":"2111.03466","title":"Learning Large Neighborhood Search Policy for Integer Programming","created":"2021-11-01","cited_by_count":35,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2309.07051","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","created":"2023-09-13","cited_by_count":15,"area":"diffusion"},{"id":"2310.15433","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2312.02682","title":"H-GAP: Humanoid Control with a Generalist Planner","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2308.02594","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2311.15341","title":"Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2308.02459","title":"Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration","created":"2023-08-04","cited_by_count":9,"area":null},{"id":"2104.10406","title":"Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching","created":"2021-04-21","cited_by_count":8,"area":null},{"id":"2206.07235","title":"Training Discrete Deep Generative Models via Gapped Straight-Through Estimator","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2404.10163","title":"EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning","created":"2024-04-15","cited_by_count":8,"area":"lr"},{"id":"2105.09992","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2301.11490","title":"Neural Episodic Control with State Abstraction","created":"2023-01-27","cited_by_count":7,"area":null},{"id":"2312.12145","title":"OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments","created":"2023-12-19","cited_by_count":7,"area":null},{"id":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"area":"deeprl"},{"id":"2111.01009","title":"Fragment-based Sequential Translation for Molecular Optimization","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"area":"deeprl"},{"id":"2405.19528","title":"Predicting Long-Term Human Behaviors in Discrete Representations via Physics-Guided Diffusion","created":"2024-05-29","cited_by_count":6,"area":"diffusion"},{"id":"2405.10310","title":"Stochastic Q-learning for Large Discrete Action Spaces","created":"2024-05-16","cited_by_count":5,"area":"deeprl"},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2210.01426","title":"Continuous Monte Carlo Graph Search","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2211.15839","title":"Continuous Neural Algorithmic Planners","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2502.21186","title":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","created":"2025-02-28","cited_by_count":4,"area":"offlinerl"},{"id":"2109.08512","title":"Soft Actor-Critic With Integer Actions","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2208.02246","title":"AdaCat: Adaptive Categorical Discretization for Autoregressive Models","created":"2022-08-03","cited_by_count":3,"area":null},{"id":"2303.17600","title":"When Learning Is Out of Reach, Reset: Generalization in Autonomous Visuomotor Reinforcement Learning","created":"2023-03-30","cited_by_count":3,"area":null},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2602.17832","title":"MePoly: Max Entropy Polynomial Policy Optimization","created":"2026-02-19","cited_by_count":3,"area":"offlinerl"},{"id":"2402.00787","title":"Learning and Calibrating Heterogeneous Bounded Rational Market Behaviour with Multi-Agent Reinforcement Learning","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2405.17618","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","created":"2024-05-27","cited_by_count":2,"area":"alignment"},{"id":"2503.01440","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2601.21841","title":"Embodied Task Planning via Graph-Informed Action Generation with Large Language Models","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2301.13324","title":"V2N Service Scaling with Deep Reinforcement Learning","created":"2023-01-30","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":"2308.16379","title":"Multi-Objective Decision Transformers for Offline Reinforcement Learning","created":"2023-08-31","cited_by_count":1,"area":"offlinerl"},{"id":"2506.00839","title":"Neural Path Guiding with Distribution Factorization","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2510.03181","title":"Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning","created":"2025-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2511.08234","title":"Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"id":"2601.23075","title":"RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2204.09500","title":"A Reinforcement Learning-based Volt-VAR Control Dataset and Testing Environment","created":"2022-04-20","cited_by_count":0,"area":null},{"id":"2401.16618","title":"A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2404.02728","title":"Unsupervised Learning of Effective Actions in Robotics","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2410.06317","title":"Learning in complex action spaces without policy gradients","created":"2024-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2502.00288","title":"Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2505.12109","title":"SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces","created":"2025-05-17","cited_by_count":0,"area":"deeprl"},{"id":"2506.16608","title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces","created":"2025-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2508.13922","title":"Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control","created":"2025-08-19","cited_by_count":0,"area":"deeprl"},{"id":"2508.14102","title":"Beyond Fixed Morphologies: Learning Graph Policies with Trust Region Compensation in Variable Action Spaces","created":"2025-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2510.17212","title":"D2C-HRHR: Discrete Actions with Double Distributional Critics for High-Risk-High-Return Tasks","created":"2025-10-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.16677","title":"Sim-to-Real Transfer via a Style-Identified Cycle Consistent Generative Adversarial Network: Zero-Shot Deployment on Robotic Manipulators through Visual Domain Adaptation","created":"2026-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.12470","title":"CLARE: Classification-based Regression for Electron Temperature Prediction","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2607.24292","title":"Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2610.17252","title":"Value-Preserving Action Quantization","created":"2026-10-12","cited_by_count":0,"area":"offlinerl"},{"id":"2610.20463","title":"Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}