Deep Deterministic Policy Gradient
PulseAugur coverage of Deep Deterministic Policy Gradient — every cluster mentioning Deep Deterministic Policy Gradient across labs, papers, and developer communities, ranked by signal.
-
新的YANN-RL方法加速了化工过程的AI控制
研究人员开发了一种名为Y-wise Affine Neural Network (YANN-RL) 的新强化学习（RL）方法，专为化工过程系统中的控制而设计。该方法旨在克服该领域RL通常面临的信任和训练时间长的挑战。通过为控制方案提供自信且可解释的起点，YANN-RL在涉及CSTR、四罐系统和萃取塔的案例研究中展示了缩短的训练时间和减少的数据需求。
-
Deep learning model achieves 95% accuracy in criminal identification
Researchers have developed a new deep learning method using the Deep Deterministic Policy Gradient (DDPG) algorithm to identify culprits in criminal investigations. This approach trains the DDPG model on crime scene dat…
-
Reinforcement learning uses symmetry and data augmentation for faster aircraft control
Researchers have developed a new method for offline reinforcement learning that leverages the symmetry of dynamical systems to improve sample efficiency. This approach uses symmetric data augmentation to enhance the sta…