Implicit Policy for Reinforcement Learning
This work addresses the challenge of flexible policy representation in reinforcement learning, offering a novel method that is incremental in nature.
The paper tackled the problem of representing complex action distributions in reinforcement learning by introducing Implicit Policy, a general class of expressive policies with efficient algorithms for entropy regularized policy gradients, and empirically showed that this approach attains desirable properties like robustness and multi-modality.
We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization combined with a rich policy class can attain desirable properties displayed under maximum entropy reinforcement learning framework, such as robustness and multi-modality.