{"total":6,"rows":[{"id":"2405.01760","title":"Reinforcement Learning-Guided Semi-Supervised Learning","created":"2024-05-02","cited_by_count":2,"area":"deeprl"},{"id":"2406.09643","title":"A Policy Gradient-Based Sequence-to-Sequence Method for Time Series Prediction","created":"2024-06-14","cited_by_count":0,"area":"deeprl"},{"id":"2510.07624","title":"From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2601.03683","title":"Rethinking Recurrent Neural Networks for Time Series Forecasting: A Reinforced Recurrent Encoder with Prediction-Oriented Proximal Policy Optimization","created":"2026-01-07","cited_by_count":0,"area":"deeprl"},{"id":"2606.12251","title":"Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2609.30258","title":"Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}