{"total":18,"rows":[{"id":"2203.02433","title":"The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights","created":"2022-03-04","cited_by_count":39,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2206.00484","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","created":"2022-05-30","cited_by_count":29,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2201.12044","title":"Generative GaitNet","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2206.12837","title":"Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer","created":"2022-06-26","cited_by_count":11,"area":null},{"id":"2201.10328","title":"ML4CO-KIDA: Knowledge Inheritance in Dataset Aggregation","created":"2022-01-25","cited_by_count":9,"area":null},{"id":"2207.03952","title":"Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks","created":"2022-07-08","cited_by_count":6,"area":null},{"id":"2309.02976","title":"Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models","created":"2023-09-06","cited_by_count":5,"area":null},{"id":"2306.04161","title":"Bidirectional GaitNet: A Bidirectional Prediction Model of Human Gait and Anatomical Conditions","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2508.18066","title":"Arnold: A multi-task, multi-embodiment muscle transformer policy","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2206.10736","title":"Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2407.11658","title":"Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion","created":"2024-07-16","cited_by_count":1,"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":"2306.15913","title":"DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2312.00268","title":"Academic competitions","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2608.24488","title":"Where Entropy Is Measured Matters: Policy Geometry in Bounded Continuous-Control PPO","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}