# Implicit Policy for Reinforcement Learning

arXiv: https://arxiv.org/abs/1806.06798 · HTML: https://mlsanity.com/paper/1806.06798/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2018.

## Built on by (most cited first, 6 of 6)

- [Learning Sampling Distributions for Model Predictive Control](https://mlsanity.com/paper/2212.02587/) (2022)
- [Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning](https://mlsanity.com/paper/2408.00309/) (2024)
- [Wasserstein Proximal Policy Gradient](https://mlsanity.com/paper/2603.02576/) (2026)
- [How to Choose a Reinforcement-Learning Algorithm](https://mlsanity.com/paper/2407.20917/) (2024)
- [Revisiting Mixture Policies in Entropy-Regularized Actor-Critic](https://mlsanity.com/paper/2605.09157/) (2026)
- [Diversity for Contingency: Learning Diverse Behaviors for Efficient Adaptation and Transfer](https://mlsanity.com/paper/2310.07493/) (2023)

## Abstract (arXiv)

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.