{"total":55,"rows":[{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2410.20018","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","created":"2024-10-26","cited_by_count":15,"area":"deeprl"},{"id":"2411.12155","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning","created":"2024-11-19","cited_by_count":10,"area":"deeprl"},{"id":"2406.16707","title":"Probabilistic Subgoal Representations for Hierarchical Reinforcement learning","created":"2024-06-24","cited_by_count":8,"area":"deeprl"},{"id":"2602.02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","created":"2026-02-02","cited_by_count":7,"area":"deeprl"},{"id":"2401.09870","title":"Reconciling Spatial and Temporal Abstractions for Goal Representation","created":"2024-01-18","cited_by_count":6,"area":"deeprl"},{"id":"2509.22442","title":"Learning to Ball: Composing Policies for Long-Horizon Basketball Moves","created":"2025-09-26","cited_by_count":6,"area":"deeprl"},{"id":"2402.04061","title":"TopoNav: Topological Navigation for Efficient Exploration in Sparse Reward Environments","created":"2024-02-06","cited_by_count":5,"area":"deeprl"},{"id":"2405.15920","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":5,"area":"deeprl"},{"id":"2504.18300","title":"Deep Reinforcement Learning Based Navigation with Macro Actions and Topological Maps","created":"2025-04-25","cited_by_count":4,"area":"deeprl"},{"id":"2506.22365","title":"Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation","created":"2025-06-27","cited_by_count":4,"area":"deeprl"},{"id":"2402.07019","title":"Informativeness of Reward Functions in Reinforcement Learning","created":"2024-02-10","cited_by_count":3,"area":"deeprl"},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2501.14992","title":"Extensive Exploration in Complex Traffic Scenarios using Hierarchical Reinforcement Learning","created":"2025-01-25","cited_by_count":3,"area":"deeprl"},{"id":"2505.11661","title":"Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2511.10872","title":"Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations","created":"2025-11-14","cited_by_count":3,"area":"deeprl"},{"id":"2402.13785","title":"Composing Reinforcement Learning Policies, with Formal Guarantees","created":"2024-02-21","cited_by_count":2,"area":"deeprl"},{"id":"2412.08574","title":"Sketch Decompositions for Classical Planning via Deep Reinforcement Learning","created":"2024-12-11","cited_by_count":2,"area":"deeprl"},{"id":"2402.14236","title":"Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning","created":"2024-02-22","cited_by_count":1,"area":"deeprl"},{"id":"2402.17050","title":"Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test","created":"2024-02-26","cited_by_count":1,"area":"deeprl"},{"id":"2407.18913","title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments","created":"2024-07-26","cited_by_count":1,"area":"deeprl"},{"id":"2409.05433","title":"State-Novelty Guided Action Persistence in Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":1,"area":"deeprl"},{"id":"2409.07416","title":"Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation","created":"2024-09-11","cited_by_count":1,"area":"deeprl"},{"id":"2505.12628","title":"Dual-Agent Reinforcement Learning for Automated Feature Generation","created":"2025-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2506.21039","title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2601.22496","title":"Action-Sufficient Goal Representations","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2602.11142","title":"Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2401.14226","title":"Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks","created":"2024-01-25","cited_by_count":0,"area":"deeprl"},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2403.10855","title":"Reinforcement Learning with Options and State Representation","created":"2024-03-16","cited_by_count":0,"area":"deeprl"},{"id":"2405.15829","title":"Spatio-temporal Value Semantics-based Abstraction for Dense Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2406.18053","title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","created":"2024-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2408.01639","title":"Coordinating Planning and Tracking in Layered Control Policies via Actor-Critic Learning","created":"2024-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2410.01739","title":"Conceptual Belief-Informed Reinforcement Learning","created":"2024-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2410.07921","title":"Boosting Hierarchical Reinforcement Learning with Meta-Learning for Complex Task Adaptation","created":"2024-10-10","cited_by_count":0,"area":"deeprl"},{"id":"2410.11262","title":"Unveiling Options with Neural Decomposition","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2501.01727","title":"Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement Learning","created":"2025-01-03","cited_by_count":0,"area":"deeprl"},{"id":"2503.18234","title":"KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies","created":"2025-03-23","cited_by_count":0,"area":"deeprl"},{"id":"2505.21410","title":"MRS: Multi-Resolution Skills for HRL Agents","created":"2025-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2506.02050","title":"Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids","created":"2025-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2507.04373","title":"Hierarchical Reinforcement Learning with Targeted Causal Interventions","created":"2025-07-06","cited_by_count":0,"area":"deeprl"},{"id":"2510.24988","title":"Enhancing Hierarchical Reinforcement Learning through Change Point Detection in Time Series","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2512.04958","title":"Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning","created":"2025-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.15119","title":"QoS-Aware Hierarchical Reinforcement Learning for Joint Link Selection and Trajectory Optimization in SAGIN-Supported UAV Mobility Management","created":"2025-12-17","cited_by_count":0,"area":"deeprl"},{"id":"2512.21412","title":"A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning","created":"2025-12-24","cited_by_count":0,"area":"deeprl"},{"id":"2601.01139","title":"Latent Space Reinforcement Learning for Multi-Robot Exploration","created":"2026-01-03","cited_by_count":0,"area":"deeprl"},{"id":"2601.19452","title":"APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2601.19810","title":"Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2602.13865","title":"Enabling Option Learning in Sparse Rewards with Hindsight Experience Replay","created":"2026-02-14","cited_by_count":0,"area":"deeprl"},{"id":"2603.06565","title":"Boosting deep Reinforcement Learning using pretraining with Logical Options","created":"2026-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2607.19232","title":"S3: Stable Subgoal Selection by Constraining Uncertainty of Coarse Dynamics in Hierarchical Reinforcement Learning","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2607.23726","title":"Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning","created":"2026-07-26","cited_by_count":0,"area":"deeprl"},{"id":"2610.17391","title":"Learning to Play: Reinforcement Learning and Games","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}