{"total":13,"rows":[{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2402.03284","title":"Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models","created":"2024-02-05","cited_by_count":6,"area":null},{"id":"2406.08315","title":"Improving Policy Optimization via $\\varepsilon$-Retrain","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2511.06430","title":"CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2310.07497","title":"Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Control","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2403.10171","title":"AUTONODE: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2412.09719","title":"TransferLight: Zero-Shot Traffic Signal Control on any Road-Network","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2501.12061","title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2606.19656","title":"DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2512.01362","title":"Directed evolution algorithm drives neural prediction","created":"2025-12-01","cited_by_count":0,"area":null}],"next_cursor":null}