{"total":62,"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":"2406.06507","title":"Verification-Guided Shielding for Deep Reinforcement Learning","created":"2024-06-10","cited_by_count":13,"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":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"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":"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":"2406.16979","title":"Understanding and Diagnosing Deep Reinforcement Learning","created":"2024-06-23","cited_by_count":6,"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":"2501.15529","title":"UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning","created":"2025-01-26","cited_by_count":5,"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":"2410.10674","title":"Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach","created":"2024-10-14","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":"2403.04050","title":"Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations","created":"2024-03-06","cited_by_count":2,"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":"2502.00346","title":"Actor Critic with Experience Replay-based automatic treatment planning for prostate cancer intensity modulated radiotherapy","created":"2025-02-01","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":"2510.20314","title":"Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses","created":"2025-10-23","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":"2402.15617","title":"Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods","created":"2024-02-23","cited_by_count":1,"area":"deeprl"},{"id":"2411.13116","title":"Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning","created":"2024-11-20","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":"2506.00801","title":"Adversarial Reinforcement Learning: A Duality-Based Approach To Solving Optimal Control Problems","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2507.03372","title":"Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization","created":"2025-07-04","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":"2602.08734","title":"Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning","created":"2026-02-09","cited_by_count":1,"area":"deeprl"},{"id":"2605.14587","title":"Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning","created":"2026-05-14","cited_by_count":1,"area":"deeprl"},{"id":"2406.11240","title":"The Benefits of Power Regularization in Cooperative Reinforcement Learning","created":"2024-06-17","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":"2505.21414","title":"A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment","created":"2025-05-27","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":"2506.23036","title":"Parameter Stress Analysis in Reinforcement Learning: Applying Synaptic Filtering to Policy Networks","created":"2025-06-28","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":"2510.12939","title":"Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement Learning","created":"2025-10-14","cited_by_count":0,"area":"deeprl"},{"id":"2511.07701","title":"Diffusion Guided Adversarial State Perturbations in Reinforcement Learning","created":"2025-11-10","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":"2601.07118","title":"Reward-Preserving Attacks For Robust Reinforcement Learning","created":"2026-01-12","cited_by_count":0,"area":"deeprl"},{"id":"2602.16543","title":"Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems","created":"2026-02-18","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":"2603.09427","title":"Impact of Markov Decision Process Design on Sim-to-Real Reinforcement Learning","created":"2026-03-10","cited_by_count":0,"area":"deeprl"},{"id":"2605.16312","title":"When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2606.16555","title":"Incentives and Evidence in Learned Service Orchestration","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.20880","title":"Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning","created":"2026-06-18","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":"2607.07029","title":"Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2609.10866","title":"Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations","created":"2026-09-09","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"},{"id":"2609.20982","title":"ASGARD: Action-Space Guard for UAV Resilience via Reinforcement Learning","created":"2026-09-17","cited_by_count":0,"area":"deeprl"},{"id":"2610.04754","title":"FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies","created":"2026-10-03","cited_by_count":0,"area":"deeprl"},{"id":"2610.06083","title":"Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}