# Entropic Risk Constrained Soft-Robust Policy Optimization

arXiv: https://arxiv.org/abs/2006.11679 · HTML: https://mlsanity.com/paper/2006.11679/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [Maximum Entropy RL (Provably) Solves Some Robust RL Problems](https://mlsanity.com/paper/2103.06257/) (2021)
- [Policy Gradient Bayesian Robust Optimization for Imitation Learning](https://mlsanity.com/paper/2106.06499/) (2021)
- [Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning](https://mlsanity.com/paper/2311.15089/) (2023)

## Abstract (arXiv)

Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by model uncertainties. Entropic risk measure is an exponential utility-based convex risk measure that satisfies many reasonable properties. In this paper, we propose an entropic risk constrained policy gradient and actor-critic algorithms that are risk-averse to the model uncertainty. We demonstrate the usefulness of our algorithms on several problem domains.