# Risk-sensitive Actor-free Policy via Convex Optimization

arXiv: https://arxiv.org/abs/2307.00141 · HTML: https://mlsanity.com/paper/2307.00141/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 30 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Input Convex Neural Networks](https://mlsanity.com/paper/1609.07152/) (2016)
- [Learning to Walk in the Real World with Minimal Human Effort](https://mlsanity.com/paper/2002.08550/) (2020)
- [Optimizing the CVaR via Sampling](https://mlsanity.com/paper/1404.3862/) (2014)
- [Worst Cases Policy Gradients](https://mlsanity.com/paper/1911.03618/) (2019)

## Built on by (most cited first, 1 of 1)

- [Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes](https://mlsanity.com/paper/2308.11267/) (2023)

## Abstract (arXiv)

Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensitive criterion based on the conditional value at risk. The risk-sensitive objective function is modeled using an input-convex neural network ensuring convexity with respect to the actions and enabling the identification of globally optimal actions through simple gradient-following methods. Experimental results demonstrate the efficacy of our approach in maintaining effective risk control.