站内快照 · 国内可打开。外网原文可能无法访问。
- 论文公开站arXiv
FERPO: Forward Entropy-Regularized Policy Optimization
Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically trained to predict returns, and accurate value predictions do not necessarily yield accurate action