{"total":43,"rows":[{"id":"2412.10713","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","created":"2024-12-14","cited_by_count":16,"area":"deeprl"},{"id":"2405.12424","title":"Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers","created":"2024-05-21","cited_by_count":14,"area":"deeprl"},{"id":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13,"area":"deeprl"},{"id":"2501.03562","title":"Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective","created":"2025-01-07","cited_by_count":10,"area":"deeprl"},{"id":"2402.12673","title":"Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies","created":"2024-02-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.20613","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","created":"2025-03-26","cited_by_count":8,"area":"deeprl"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2402.03590","title":"Assessing the Impact of Distribution Shift on Reinforcement Learning Performance","created":"2024-02-05","cited_by_count":7,"area":"deeprl"},{"id":"2503.20844","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","created":"2025-03-26","cited_by_count":7,"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":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2402.02165","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","created":"2024-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2405.11432","title":"On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks","created":"2024-05-19","cited_by_count":4,"area":"deeprl"},{"id":"2406.18062","title":"Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents","created":"2024-06-26","cited_by_count":4,"area":"deeprl"},{"id":"2507.17070","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","created":"2025-07-22","cited_by_count":3,"area":"deeprl"},{"id":"2406.03862","title":"Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation","created":"2024-06-06","cited_by_count":2,"area":"deeprl"},{"id":"2406.04724","title":"On Minimizing Adversarial Counterfactual Error in Adversarial RL","created":"2024-06-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.17248","title":"Backdoors in DRL: Four Environments Focusing on In-distribution Triggers","created":"2025-05-22","cited_by_count":2,"area":"deeprl"},{"id":"2512.18957","title":"Online Robust Reinforcement Learning with General Function Approximation","created":"2025-12-22","cited_by_count":2,"area":"deeprl"},{"id":"2402.03146","title":"A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning","created":"2024-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.17667","title":"CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2506.22423","title":"ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks","created":"2025-06-27","cited_by_count":1,"area":"deeprl"},{"id":"2507.04883","title":"Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning","created":"2025-07-07","cited_by_count":1,"area":"deeprl"},{"id":"2510.16650","title":"Adversarial Reinforcement Learning for Robust Control of Fixed-Wing Aircraft under Model Uncertainty","created":"2025-10-18","cited_by_count":1,"area":"deeprl"},{"id":"2602.00399","title":"Reinforcement Learning for Control Systems with Time Delays: A Comprehensive Survey","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2404.08089","title":"Efficient Duple Perturbation Robustness in Low-rank MDPs","created":"2024-04-11","cited_by_count":0,"area":"deeprl"},{"id":"2405.16830","title":"Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation","created":"2024-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2408.00023","title":"On the Perturbed States for Transformed Input-robust Reinforcement Learning","created":"2024-07-31","cited_by_count":0,"area":"deeprl"},{"id":"2408.09112","title":"Training Verifiably Robust Agents Using Set-Based Reinforcement Learning","created":"2024-08-17","cited_by_count":0,"area":"deeprl"},{"id":"2409.00418","title":"Robust off-policy Reinforcement Learning via Soft Constrained Adversary","created":"2024-08-31","cited_by_count":0,"area":"deeprl"},{"id":"2412.07686","title":"Optimizing Sensor Redundancy in Sequential Decision-Making Problems","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2506.06891","title":"Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2506.08961","title":"Towards Robust Deep Reinforcement Learning against Environmental State Perturbation","created":"2025-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2506.16753","title":"Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation","created":"2025-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2506.21127","title":"Meta Policy Switching for Secure UAV Deconfliction in Adversarial Airspace","created":"2025-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.10937","title":"Neutral Agent-based Adversarial Policy Learning against Deep Reinforcement Learning in Multi-party Open Systems","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.11899","title":"ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.13792","title":"Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach","created":"2025-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2512.01228","title":"On the Tension Between Optimality and Adversarial Robustness in Policy Optimization","created":"2025-12-01","cited_by_count":0,"area":"deeprl"},{"id":"2602.19582","title":"Advantage-based Temporal Attack in Reinforcement Learning","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2606.29867","title":"RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learning","created":"2026-06-29","cited_by_count":0,"area":"deeprl"},{"id":"2609.13044","title":"Robust Policy Optimization via Adversarial Importance Sampling","created":"2026-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2609.15297","title":"Admissable: Training Reinforcement Learning Agents against Adversarial Missingness","created":"2026-09-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}