{"total":51,"rows":[{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2403.15267","title":"Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies","created":"2024-03-22","cited_by_count":7,"area":"deeprl"},{"id":"2410.20487","title":"Efficient Diversity-based Experience Replay for Deep Reinforcement Learning","created":"2024-10-27","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2405.13574","title":"Reinforcement Learning for Adaptive MCMC","created":"2024-05-22","cited_by_count":6,"area":"deeprl"},{"id":"2406.19825","title":"Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems","created":"2024-06-28","cited_by_count":3,"area":"deeprl"},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2503.05905","title":"Performance Comparisons of Reinforcement Learning Algorithms for Sequential Experimental Design","created":"2025-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","cited_by_count":3,"area":"deeprl"},{"id":"2512.19366","title":"Learning General Policies with Policy Gradient Methods","created":"2025-12-22","cited_by_count":3,"area":"deeprl"},{"id":"2405.04549","title":"ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces","created":"2024-05-05","cited_by_count":2,"area":"deeprl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2401.17976","title":"Circuit Partitioning for Multi-Core Quantum Architectures with Deep Reinforcement Learning","created":"2024-01-31","cited_by_count":1,"area":"deeprl"},{"id":"2402.11515","title":"Optimal Parallelization Strategies for Active Flow Control in Deep Reinforcement Learning-Based Computational Fluid Dynamics","created":"2024-02-18","cited_by_count":1,"area":"deeprl"},{"id":"2402.13219","title":"Analyzing Operator States and the Impact of AI-Enhanced Decision Support in Control Rooms: A Human-in-the-Loop Specialized Reinforcement Learning Framework for Intervention Strategies","created":"2024-02-20","cited_by_count":1,"area":"deeprl"},{"id":"2404.08423","title":"SIR-RL: Reinforcement Learning for Optimized Policy Control during Epidemiological Outbreaks in Emerging Market and Developing Economies","created":"2024-04-12","cited_by_count":1,"area":"deeprl"},{"id":"2406.09079","title":"Hadamard Representation: Scaffolding Performance Across Model-free RL","created":"2024-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2408.07712","title":"Introduction to Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2408.15751","title":"Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion","created":"2024-08-28","cited_by_count":1,"area":"deeprl"},{"id":"2409.17411","title":"Enhancing Interpretability in Deep Reinforcement Learning through Semantic Clustering","created":"2024-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2410.09368","title":"Towards a Domain-Specific Modelling Environment for Reinforcement Learning","created":"2024-10-12","cited_by_count":1,"area":"deeprl"},{"id":"2410.20550","title":"Deep Reinforcement Learning Agents for Strategic Production Policies in Microeconomic Market Simulations","created":"2024-10-27","cited_by_count":1,"area":"deeprl"},{"id":"2501.14443","title":"Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agent","created":"2025-01-24","cited_by_count":1,"area":"deeprl"},{"id":"2402.09075","title":"Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards","created":"2024-02-14","cited_by_count":0,"area":"deeprl"},{"id":"2403.10006","title":"Graph Enhanced Reinforcement Learning for Effective Group Formation in Collaborative Problem Solving","created":"2024-03-15","cited_by_count":0,"area":"deeprl"},{"id":"2403.18219","title":"From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries","created":"2024-03-27","cited_by_count":0,"area":"deeprl"},{"id":"2406.04575","title":"Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning","created":"2024-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2412.04829","title":"Learning-based Control for Tendon-Driven Continuum Robotic Arms","created":"2024-12-06","cited_by_count":0,"area":"deeprl"},{"id":"2502.20348","title":"Improving the Efficiency of a Deep Reinforcement Learning-Based Power Management System for HPC Clusters Using Curriculum Learning","created":"2025-02-27","cited_by_count":0,"area":"deeprl"},{"id":"2504.05397","title":"Physics-informed Modularized Neural Network for Advanced Building Control by Deep Reinforcement Learning","created":"2025-04-07","cited_by_count":0,"area":"deeprl"},{"id":"2505.10988","title":"DRL-Based Injection Molding Process Parameter Optimization for Adaptive and Profitable Production","created":"2025-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2506.11912","title":"Breaking Habits: On the Role of the Advantage Function in Learning Causal State Representations","created":"2025-06-13","cited_by_count":0,"area":"deeprl"},{"id":"2509.11161","title":"Dual Reinforcement Learning Synergy in Resource Allocation: Emergence of Self-Organized Momentum Strategy","created":"2025-09-14","cited_by_count":0,"area":"deeprl"},{"id":"2510.15120","title":"Procedural Game Level Design with Deep Reinforcement Learning","created":"2025-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2511.02969","title":"Value of Information-Enhanced Exploration in Bootstrapped DQN","created":"2025-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2511.18000","title":"Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning","created":"2025-11-22","cited_by_count":0,"area":"deeprl"},{"id":"2512.18146","title":"On Swarm Leader Identification using Probing Policies","created":"2025-12-20","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":"2601.16866","title":"Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators","created":"2026-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2602.19837","title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2602.24081","title":"Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning","created":"2026-02-27","cited_by_count":0,"area":"deeprl"},{"id":"2604.01886","title":"When does learning pay off? A study on DRL-based dynamic algorithm configuration for carbon-aware scheduling","created":"2026-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2604.11463","title":"To Learn or Not to Learn: A Litmus Test for Using Reinforcement Learning in Control","created":"2026-04-13","cited_by_count":0,"area":"deeprl"},{"id":"2606.03201","title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.16177","title":"Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.18368","title":"Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability","created":"2026-07-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.19628","title":"HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2607.25985","title":"Physics-Aware End-to-End Deep Reinforcement Learning for Quadcopter Control with Actuator Dynamics","created":"2026-07-28","cited_by_count":0,"area":"deeprl"},{"id":"2608.09628","title":"Satellite Trajectory Optimization via Proximal Policy Optimization for Space Debris Avoidance","created":"2026-08-10","cited_by_count":0,"area":"deeprl"},{"id":"2608.17628","title":"Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision","created":"2026-08-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}