{"total":73,"rows":[{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2505.02835","title":"R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning","created":"2025-05-05","cited_by_count":65,"area":"mllm"},{"id":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"area":null},{"id":"2202.07141","title":"Machine Learning in Aerodynamic Shape Optimization","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2103.04847","title":"Adversarial Reinforcement Learning for Procedural Content Generation","created":"2021-03-08","cited_by_count":36,"area":null},{"id":"2505.18134","title":"VideoGameBench: Can Vision-Language Models complete popular video games?","created":"2025-05-23","cited_by_count":36,"area":"mllm"},{"id":"2209.13900","title":"Disentangling Transfer in Continual Reinforcement Learning","created":"2022-09-28","cited_by_count":33,"area":null},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2510.15047","title":"Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective","created":"2025-10-16","cited_by_count":28,"area":"wm"},{"id":"2103.11575","title":"Learn-to-Race: A Multimodal Control Environment for Autonomous Racing","created":"2021-03-22","cited_by_count":23,"area":null},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2406.03704","title":"Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking","created":"2024-06-06","cited_by_count":19,"area":"deeprl"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2103.08741","title":"Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification","created":"2021-03-15","cited_by_count":12,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"id":"2506.15068","title":"Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation","created":"2025-06-18","cited_by_count":11,"area":"alignment"},{"id":"2212.03830","title":"A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat","created":"2022-12-05","cited_by_count":10,"area":null},{"id":"2103.04067","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","created":"2021-03-06","cited_by_count":9,"area":null},{"id":"2103.09159","title":"Learning to Shape Rewards using a Game of Two Partners","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2509.03682","title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2207.08379","title":"Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2403.15267","title":"Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies","created":"2024-03-22","cited_by_count":7,"area":"deeprl"},{"id":"2505.24710","title":"Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2306.00035","title":"ROSARL: Reward-Only Safe Reinforcement Learning","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2409.19816","title":"Grounded Curriculum Learning","created":"2024-09-29","cited_by_count":5,"area":"deeprl"},{"id":"2410.02829","title":"LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents","created":"2024-10-01","cited_by_count":5,"area":"agents"},{"id":"2502.20341","title":"Safety Representations for Safer Policy Learning","created":"2025-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2106.02390","title":"Online reinforcement learning with sparse rewards through an active inference capsule","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2402.04567","title":"OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences","created":"2024-02-07","cited_by_count":3,"area":"offlinerl"},{"id":"2405.15908","title":"Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine","created":"2024-05-24","cited_by_count":3,"area":"deeprl"},{"id":"2407.14486","title":"Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent","created":"2024-07-19","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":"2408.07962","title":"Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning","created":"2024-08-15","cited_by_count":3,"area":"deeprl"},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2508.13121","title":"Bayesian Optimization-based Search for Agent Control in Automated Game Testing","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2306.11466","title":"Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving Maneuvers","created":"2023-06-20","cited_by_count":2,"area":"driving"},{"id":"2308.12438","title":"Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2502.10303","title":"Reinforcement Learning in Strategy-Based and Atari Games: A Review of Google DeepMinds Innovations","created":"2025-02-14","cited_by_count":2,"area":"deeprl"},{"id":"2511.19355","title":"Leveraging LLMs for reward function design in reinforcement learning control tasks","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2601.20753","title":"GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning","created":"2026-01-28","cited_by_count":2,"area":"deeprl"},{"id":"2108.05701","title":"An Approach to Partial Observability in Games: Learning to Both Act and Observe","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2112.04494","title":"Deep Q-Learning Market Makers in a Multi-Agent Simulated Stock Market","created":"2021-12-08","cited_by_count":1,"area":null},{"id":"2204.11370","title":"Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing","created":"2022-04-24","cited_by_count":1,"area":null},{"id":"2208.06033","title":"Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2304.00026","title":"Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2311.16339","title":"Reward Shaping for Improved Learning in Real-time Strategy Game Play","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2312.14824","title":"An investigation of belief-free DRL and MCTS for inspection and maintenance planning","created":"2023-12-22","cited_by_count":1,"area":null},{"id":"2408.06818","title":"Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"offlinerl"},{"id":"2410.04322","title":"Toward Debugging Deep Reinforcement Learning Programs with RLExplorer","created":"2024-10-06","cited_by_count":1,"area":"deeprl"},{"id":"2410.16653","title":"Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games","created":"2024-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2410.21601","title":"The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure","created":"2024-10-28","cited_by_count":1,"area":"deeprl"},{"id":"2410.23393","title":"Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2503.21668","title":"Cognitive Science-Inspired Evaluation of Core Capabilities for Object Understanding in AI","created":"2025-03-27","cited_by_count":1,"area":"wm"},{"id":"2105.09719","title":"Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics","created":"2021-05-20","cited_by_count":0,"area":null},{"id":"2106.03688","title":"A Computational Model of Representation Learning in the Brain Cortex, Integrating Unsupervised and Reinforcement Learning","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2208.00003","title":"RangL: A Reinforcement Learning Competition Platform","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2208.07307","title":"Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning","created":"2022-07-21","cited_by_count":0,"area":null},{"id":"2208.10327","title":"Incorporating Rivalry in Reinforcement Learning for a Competitive Game","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2209.05859","title":"A new Reinforcement Learning framework to discover natural flavor molecules","created":"2022-09-13","cited_by_count":0,"area":null},{"id":"2211.03136","title":"Design Process is a Reinforcement Learning Problem","created":"2022-11-06","cited_by_count":0,"area":null},{"id":"2306.13879","title":"Action Q-Transformer: Visual Explanation in Deep Reinforcement Learning with Encoder-Decoder Model using Action Query","created":"2023-06-24","cited_by_count":0,"area":null},{"id":"2310.16592","title":"Over-the-air Federated Policy Gradient","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2505.13638","title":"4Hammer: a board-game reinforcement learning environment for the hour long time frame","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2603.06608","title":"Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.19721","title":"OnDeFog: Online Decision Transformer under Frame Dropping","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2607.16177","title":"Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.16999","title":"Counterfactual Shapley Credit Assignment","created":"2026-07-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}