{"total":16,"rows":[{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55,"area":null},{"id":"2203.08553","title":"PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration","created":"2022-03-16","cited_by_count":23,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2312.11337","title":"Challenges for Reinforcement Learning in Quantum Circuit Design","created":"2023-12-18","cited_by_count":9,"area":null},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2203.00636","title":"Distributional Reinforcement Learning for Scheduling of Chemical Production Processes","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2305.01461","title":"Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2309.08611","title":"Maneuver Decision-Making Through Proximal Policy Optimization And Monte Carlo Tree Search","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2508.07804","title":"Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2602.18716","title":"Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2606.10979","title":"Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.26574","title":"Revisiting Action Factorization for Complex Action Spaces","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.27627","title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":null}