{"total":21,"rows":[{"id":"2402.10033","title":"Neural Network Approaches for Parameterized Optimal Control","created":"2024-02-15","cited_by_count":8,"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":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2401.06604","title":"Identifying Policy Gradient Subspaces","created":"2024-01-12","cited_by_count":5,"area":"deeprl"},{"id":"2402.05476","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","created":"2024-02-08","cited_by_count":5,"area":"deeprl"},{"id":"2410.12136","title":"Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration","created":"2024-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2401.15484","title":"R$\\times$R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training","created":"2024-01-27","cited_by_count":3,"area":"deeprl"},{"id":"2409.18827","title":"ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning","created":"2024-09-27","cited_by_count":3,"area":"deeprl"},{"id":"2507.00518","title":"Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling","created":"2025-07-01","cited_by_count":3,"area":"deeprl"},{"id":"2511.11592","title":"Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2404.01598","title":"Extremum-Seeking Action Selection for Accelerating Policy Optimization","created":"2024-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2409.15963","title":"Provably Efficient Exploration in Inverse Constrained Reinforcement Learning","created":"2024-09-24","cited_by_count":1,"area":"deeprl"},{"id":"2604.12645","title":"Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring","created":"2026-04-14","cited_by_count":1,"area":"deeprl"},{"id":"2407.10835","title":"Exploration in Knowledge Transfer Utilizing Reinforcement Learning","created":"2024-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2504.11907","title":"A Graph-Based Reinforcement Learning Approach with Frontier Potential Based Reward for Safe Cluttered Environment Exploration","created":"2025-04-16","cited_by_count":0,"area":"deeprl"},{"id":"2511.15358","title":"Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph Attention","created":"2025-11-19","cited_by_count":0,"area":"deeprl"},{"id":"2511.19808","title":"Learning to Clean: Reinforcement Learning for Noisy Label Correction","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2602.00460","title":"Search Inspired Exploration in Reinforcement Learning","created":"2026-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2602.18856","title":"Issues with Measuring Task Complexity via Random Policies in Robotic Tasks","created":"2026-02-21","cited_by_count":0,"area":"deeprl"},{"id":"2610.01781","title":"Q-Learning for Reachability in MEC-Free MDPs","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}