Bei Peng

Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients

2021 · arXiv (Cornell University)

Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios. However, there is a significant performance gap between state-of-the-art policy gradient and …

A Model Fusion Distributed Kalman Filter For Non-Gaussian Observation Noise

2023 · arXiv (Cornell University)

Wireless sensor networks (WSNs) represent a critical research domain within the Internet of Things (IoT) technology. The distributed Kalman filter (DKF) has garnered significant attention as an information fusion method for WSNs. However, effectively handling …

Gradable ChatGPT Translation Evaluation

2024 · arXiv (Cornell University)

ChatGPT, as a language model based on large-scale pre-training, has exerted a profound influence on the domain of machine translation. In ChatGPT, a "Prompt" refers to a segment of text or instruction employed to steer …