Offline Reinforcement Learning
Offline reinforcement learning (RL) aims to train agents using pre-collected data, eliminating the need for costly and potentially risky online interactions with the environment. Current research focuses on addressing challenges like distributional shift (mismatch between training and target data) and improving generalization across diverse tasks, employing model architectures such as transformers, convolutional networks, and diffusion models, along with algorithms like conservative Q-learning and decision transformers. These advancements are significant for deploying RL in real-world applications where online learning is impractical or unsafe, impacting fields ranging from robotics and healthcare to personalized recommendations and autonomous systems.
Papers
Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning
Yen-Ru Lai, Fu-Chieh Chang, Pei-Yuan Wu
Domain Adaptation for Offline Reinforcement Learning with Limited Samples
Weiqin Chen, Sandipan Mishra, Santiago Paternain
Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation
Woo Kyung Kim, Minjong Yoo, Honguk Woo
Offline Model-Based Reinforcement Learning with Anti-Exploration
Padmanaba Srinivasan, William Knottenbelt
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Yun Qu, Boyuan Wang, Jianzhun Shao, Yuhang Jiang, Chen Chen, Zhenbin Ye, Lin Liu, Junfeng Yang, Lin Lai, Hongyang Qin, Minwen Deng, Juchao Zhuo, Deheng Ye, Qiang Fu, Wei Yang, Guang Yang, Lanxiao Huang, Xiangyang Ji
Integrating Multi-Modal Input Token Mixer Into Mamba-Based Decision Models: Decision MetaMamba
Wall Kim