{"total":12,"rows":[{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2311.01388","title":"Time-series Generation by Contrastive Imitation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2101.11331","title":"OffCon$^3$: What is state of the art anyway?","created":"2021-01-27","cited_by_count":5,"area":null},{"id":"2203.09809","title":"Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio","created":"2022-03-18","cited_by_count":5,"area":null},{"id":"2104.03807","title":"A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Control","created":"2021-04-08","cited_by_count":3,"area":null},{"id":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2208.04517","title":"Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning","created":"2022-08-09","cited_by_count":1,"area":null},{"id":"2310.17173","title":"DSAC-C: Constrained Maximum Entropy for Robust Discrete Soft-Actor Critic","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2601.21177","title":"Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling","created":"2026-01-29","cited_by_count":0,"area":null}],"next_cursor":null}