【论文原文】:Reinforcement Learning in Continuous Time and Space: A Stochastic Control Approach
【作者信息】:
Haoran Wang |
Thaleia Zariphopoulou
Xun Yu Zhou |
获取地址:19-144.pdf (jmlr.org)https://www.jmlr.org/papers/volume21/19-144/19-144.pdf博主关键词:Reinforcement learning, entropy regularization, stochastic control, relaxed
control, linear-quadratic, Gaussian distribution
摘要:
We consider reinforcement learning (RL) in