{"total":79,"rows":[{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2405.19153","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","created":"2024-05-29","cited_by_count":26,"area":"deeprl"},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2405.17416","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","created":"2024-05-27","cited_by_count":14,"area":"deeprl"},{"id":"2402.03479","title":"DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design","created":"2024-02-05","cited_by_count":11,"area":"deeprl"},{"id":"2406.03997","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","created":"2024-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2511.12779","title":"Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation","created":"2025-11-16","cited_by_count":8,"area":"deeprl"},{"id":"2410.03376","title":"Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization","created":"2024-10-04","cited_by_count":6,"area":"deeprl"},{"id":"2410.10834","title":"Focus On What Matters: Separated Models For Visual-Based RL Generalization","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2504.10865","title":"Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iteration","created":"2025-04-15","cited_by_count":6,"area":"deeprl"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2402.12181","title":"Revisiting Data Augmentation in Deep Reinforcement Learning","created":"2024-02-19","cited_by_count":5,"area":"deeprl"},{"id":"2407.06756","title":"Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning","created":"2024-07-09","cited_by_count":4,"area":"deeprl"},{"id":"2410.02236","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","created":"2024-10-03","cited_by_count":4,"area":"deeprl"},{"id":"2505.08361","title":"Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning","created":"2025-05-13","cited_by_count":4,"area":"deeprl"},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2403.13245","title":"Federated reinforcement learning for robot motion planning with zero-shot generalization","created":"2024-03-20","cited_by_count":3,"area":"deeprl"},{"id":"2407.15656","title":"Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN","created":"2024-07-22","cited_by_count":3,"area":"deeprl"},{"id":"2409.17469","title":"VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain","created":"2024-09-26","cited_by_count":3,"area":"deeprl"},{"id":"2410.12983","title":"Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2507.06602","title":"Generalization in Reinforcement Learning for Radio Access Networks","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2406.01952","title":"Improving Generalization in Aerial and Terrestrial Mobile Robots Control Through Delayed Policy Learning","created":"2024-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2407.20651","title":"Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations","created":"2024-07-30","cited_by_count":2,"area":"deeprl"},{"id":"2409.10048","title":"Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2501.12823","title":"To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning","created":"2025-01-22","cited_by_count":2,"area":"deeprl"},{"id":"2506.05418","title":"Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2509.20008","title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation","created":"2025-09-24","cited_by_count":2,"area":"deeprl"},{"id":"2604.01142","title":"Planning for Change: Reinforcement Learning Combined with Bounded Extremum Seeking for Robotic Control under Distribution Shift","created":"2026-04-01","cited_by_count":2,"area":"deeprl"},{"id":"2501.02481","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","created":"2025-01-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.11136","title":"A Novel Switch-Type Policy Network for Resource Allocation Problems: Technical Report","created":"2025-01-19","cited_by_count":1,"area":"deeprl"},{"id":"2501.17384","title":"A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2502.17983","title":"Provable Performance Bounds for Digital Twin-driven Deep Reinforcement Learning in Wireless Networks: A Novel Digital-Twin Bisimulation Metric","created":"2025-02-25","cited_by_count":1,"area":"deeprl"},{"id":"2503.01146","title":"Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation","created":"2025-03-03","cited_by_count":1,"area":"deeprl"},{"id":"2505.16581","title":"How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning","created":"2025-05-22","cited_by_count":1,"area":"deeprl"},{"id":"2506.16352","title":"Data-Driven Policy Mapping for Safe RL-based Energy Management Systems","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2507.03068","title":"Mitigating Goal Misgeneralization via Minimax Regret","created":"2025-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2509.21234","title":"AbideGym: Turning Static RL Worlds into Adaptive Challenges","created":"2025-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2601.14957","title":"Improving Regret Approximation for Unsupervised Dynamic Environment Generation","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2601.21094","title":"Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed","created":"2026-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2602.05619","title":"Mode-Dependent Rectification for Stable PPO Training","created":"2026-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2608.26469","title":"Active Curriculum Refinement for Reinforcement Learning","created":"2026-08-26","cited_by_count":1,"area":"deeprl"},{"id":"2403.07979","title":"Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning","created":"2024-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2406.08069","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","created":"2024-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2406.14324","title":"Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2409.13108","title":"Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning","created":"2024-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2410.16821","title":"Guiding Reinforcement Learning with Incomplete System Dynamics","created":"2024-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2411.02998","title":"Accelerating Task Generalisation with Multi-Level Skill Hierarchies","created":"2024-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"id":"2503.08867","title":"Zero-Shot Action Generalization with Limited Observations","created":"2025-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2503.14809","title":"Learning with Expert Abstractions for Efficient Multi-Task Continuous Control","created":"2025-03-19","cited_by_count":0,"area":"deeprl"},{"id":"2505.01953","title":"Training Environment for High Performance Reinforcement Learning","created":"2025-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2506.21367","title":"rQdia: Regularizing Q-Value Distributions With Image Augmentation","created":"2025-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2508.00283","title":"Neural Co-state Projection Regulator: A Model-free Paradigm for Real-time Optimal Control with Input Constraints","created":"2025-08-01","cited_by_count":0,"area":"deeprl"},{"id":"2508.11204","title":"Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation","created":"2025-08-15","cited_by_count":0,"area":"deeprl"},{"id":"2509.12531","title":"Pre-trained Visual Representations Generalize Where it Matters in Model-Based Reinforcement Learning","created":"2025-09-16","cited_by_count":0,"area":"deeprl"},{"id":"2509.23209","title":"Context Value Informed In-Context Reinforcement Learning","created":"2025-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2509.23750","title":"An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms","created":"2025-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2511.03473","title":"Reinforcement Learning Using known Invariances","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2511.20234","title":"Leveraging weights signals -- Predicting and improving generalizability in reinforcement learning","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2601.14232","title":"KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"deeprl"},{"id":"2602.04412","title":"HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation","created":"2026-02-04","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":"2603.11600","title":"Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.02867","title":"Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.07057","title":"From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.12206","title":"Train Short, Act Long: Multistability and the Horizon Independence of Recurrent Policies","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2606.00880","title":"Task diversity produces systematic transfer but inhibits continual reinforcement learning","created":"2026-05-30","cited_by_count":0,"area":"deeprl"},{"id":"2606.16236","title":"Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.16933","title":"A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.27032","title":"State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading","created":"2026-06-25","cited_by_count":0,"area":"deeprl"},{"id":"2606.27348","title":"Bridging Performance and Generalization in Reinforcement Learning for Agile Flight","created":"2026-06-25","cited_by_count":0,"area":"deeprl"},{"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":"2609.32532","title":"What Does a ProcGen Generalization Gap Measure? Action Rules, Residual Entropy, and the Missing Random Floor","created":"2026-09-26","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}