{"list":"other","total":67,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"2010.00827","title":"Neural Thompson Sampling","created":"2020-10-02","cited_by_count":128},{"id":"1807.07838","title":"TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time","created":"2018-07-20","cited_by_count":108},{"id":"2010.09470","title":"Dos and Don'ts of Machine Learning in Computer Security","created":"2020-10-19","cited_by_count":102},{"id":"1906.05799","title":"Deep Reinforcement Learning for Cyber Security","created":"2019-06-13","cited_by_count":95},{"id":"2004.05682","title":"PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning","created":"2020-04-12","cited_by_count":67},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65},{"id":"2005.07099","title":"Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":63},{"id":"1801.08917","title":"Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning","created":"2018-01-26","cited_by_count":61},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59},{"id":"1907.05587","title":"Stateful Detection of Black-Box Adversarial Attacks","created":"2019-07-12","cited_by_count":56},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47},{"id":"2207.12355","title":"Developing Optimal Causal Cyber-Defence Agents via Cyber Security Simulation","created":"2022-07-25","cited_by_count":37},{"id":"1808.09700","title":"Evaluating Fuzz Testing","created":"2018-08-29","cited_by_count":32},{"id":"2408.03906","title":"Achieving Human Level Competitive Robot Table Tennis","created":"2024-08-07","cited_by_count":27},{"id":"1907.02908","title":"On Inductive Biases in Deep Reinforcement Learning","created":"2019-07-05","cited_by_count":24},{"id":"2310.13565","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","created":"2023-10-20","cited_by_count":19},{"id":"1808.05770","title":"Reinforcement Learning for Autonomous Defence in Software-Defined Networking","created":"2018-08-17","cited_by_count":17},{"id":"2306.09318","title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","created":"2023-06-15","cited_by_count":17},{"id":"2108.07124","title":"Using Cyber Terrain in Reinforcement Learning for Penetration Testing","created":"2021-08-16","cited_by_count":16},{"id":"2412.07165","title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","created":"2024-12-10","cited_by_count":15},{"id":"1801.04589","title":"Deep Reinforcement Fuzzing","created":"2018-01-14","cited_by_count":14},{"id":"2512.09549","title":"Chasing Shadows: Pitfalls in LLM Security Research","created":"2025-12-10","cited_by_count":13},{"id":"1906.08805","title":"Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning","created":"2019-06-20","cited_by_count":12},{"id":"2208.12897","title":"ATTRITION: Attacking Static Hardware Trojan Detection Techniques Using Reinforcement Learning","created":"2022-08-26","cited_by_count":11},{"id":"2303.06280","title":"Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks","created":"2023-03-11","cited_by_count":11},{"id":"2101.02636","title":"Deep Reinforcement Learning for Black-Box Testing of Android Apps","created":"2021-01-07","cited_by_count":10},{"id":"2208.08025","title":"AutoCAT: Reinforcement Learning for Automated Exploration of Cache-Timing Attacks","created":"2022-08-17","cited_by_count":9},{"id":"2312.04940","title":"Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning","created":"2023-12-08","cited_by_count":9},{"id":"2402.01359","title":"TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (Extended Version)","created":"2024-02-02","cited_by_count":9},{"id":"2302.10739","title":"MalProtect: Stateful Defense Against Adversarial Query Attacks in ML-based Malware Detection","created":"2023-02-21","cited_by_count":8},{"id":"2405.10220","title":"SoK: Prudent Evaluation Practices for Fuzzing","created":"2024-05-16","cited_by_count":8},{"id":"2408.08594","title":"DeepREST: Automated Test Case Generation for REST APIs Exploiting Deep Reinforcement Learning","created":"2024-08-16","cited_by_count":8},{"id":"2504.02132","title":"One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image","created":"2025-04-02","cited_by_count":8},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7},{"id":"2101.03118","title":"Simulating SQL Injection Vulnerability Exploitation Using Q-Learning Reinforcement Learning Agents","created":"2021-01-08","cited_by_count":6},{"id":"2305.11039","title":"Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation","created":"2023-05-18","cited_by_count":6},{"id":"2312.13435","title":"The Adaptive Arms Race: Redefining Robustness in AI Security","created":"2023-12-20","cited_by_count":5},{"id":"2412.15991","title":"APIRL: Deep Reinforcement Learning for REST API Fuzzing","created":"2024-12-20","cited_by_count":4},{"id":"2210.02840","title":"Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection","created":"2022-10-06","cited_by_count":3},{"id":"2308.16562","title":"The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning","created":"2023-08-31","cited_by_count":3},{"id":"2402.19027","title":"How to Train your Antivirus: RL-based Hardening through the Problem-Space","created":"2024-02-29","cited_by_count":3},{"id":"2503.04262","title":"Guidelines for Applying RL and MARL in Cybersecurity Applications","created":"2025-03-06","cited_by_count":2}],"next_cursor":null}