{"total":22,"rows":[{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24,"area":null},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2405.07162","title":"Learning Reward for Robot Skills Using Large Language Models via Self-Alignment","created":"2024-05-12","cited_by_count":20,"area":null},{"id":"2104.02180","title":"AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control","created":"2021-04-05","cited_by_count":18,"area":null},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2505.04961","title":"Physics-Based Motion Imitation with Adversarial Differential Discriminators","created":"2025-05-08","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"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":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2205.01906","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2605.15417","title":"$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2301.11461","title":"Learning to Generate All Feasible Actions","created":"2023-01-26","cited_by_count":2,"area":null},{"id":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2606.27475","title":"Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2410.22081","title":"Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2505.08899","title":"Bounding Neyman-Pearson Region with $f$-Divergences","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2510.07562","title":"EBGAN-MDN: An Energy-Based Adversarial Framework for Multi-Modal Behavior Cloning","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2609.07303","title":"Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}