Learning from Demonstration

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 93

All topics

Policy Improvement with Style-Specific Demonstrations
Jun 20, 2025Lingfeng Li, Yunlong Lu, Yongyi Wang +1Reinforcement Learning Game-Playing Agents
School of Computer Science, Peking University, Beijing 100871, China
HERB: Human-augmented Efficient Reinforcement learning for Bin-packing
Apr 23, 2025Gojko Perovic, Nuno Ferreira Duarte, Atabak Dehban +3Robotic RL Robotics
BioRobotics Institute, Scuola Superiore Sant’Anna, Pisa, Italy, and with the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, Italy. · Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal.
OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations
Date pendingYixiong Xiao, Lang An, Hucheng Yang +9Computer-Use Agents GUI Automation
Baidu, Inc., Beijing, China · Ningxia Electric Power Engineering Co., Ltd., China

Jun 20, 2025, cs.AIJ/K move · Enter open · S save

Policy Improvement with Style-Specific Demonstrations

Lingfeng Li, Yunlong Lu, Yongyi Wang, Wenxin Li

School of Computer Science, Peking University, Beijing 100871, China

Reinforcement Learning Game-Playing Agents Offline RL Learning from Demonstration Proximal Policy Optimization

Open paper AskPDF arXiv

Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency, whereas methods based on evolution algorithms generate agents with diverse play styles but exhibit subpar performance compared to RL methods. To address this gap, this paper proposes Mixed Proximal Policy Optimization (MPPO), a method designed to improve the proficiency of existing suboptimal agents while retaining their distinct styles. MPPO unifies loss objectives for both online and offline samples and introduces an implicit constraint to approximate demonstrator policies by adjusting the empirical distribution of samples. Empirical results across environments of varying scales demonstrate that MPPO achieves proficiency levels comparable to, or even superior to, pure online algorithms while preserving demonstrators' play styles. This work presents an effective approach for generating highly proficient and diverse game agents, ultimately contributing to more engaging gameplay experiences.

Momentum

Related topics

Latest papers 93

Policy Improvement with Style-Specific Demonstrations

HERB: Human-augmented Efficient Reinforcement learning for Bin-packing

OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations