# Risk-Averse Planning Under Uncertainty

arXiv: https://arxiv.org/abs/1909.12499 · HTML: https://mlsanity.com/paper/1909.12499/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 11 of 11)

- [STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation](https://mlsanity.com/paper/2103.02828/) (2021)
- [Driving Through Ghosts: Behavioral Cloning with False Positives](https://mlsanity.com/paper/2008.12969/) (2020)
- [Risk-Averse Stochastic Shortest Path Planning](https://mlsanity.com/paper/2103.14727/) (2021)
- [Two steps to risk sensitivity](https://mlsanity.com/paper/2111.06803/) (2021)
- [STL Robustness Risk over Discrete-Time Stochastic Processes](https://mlsanity.com/paper/2104.01503/) (2021)
- [Risk-Averse Decision Making Under Uncertainty](https://mlsanity.com/paper/2109.04082/) (2021)
- [Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function](https://mlsanity.com/paper/2601.20554/) (2026)
- [A Risk-Averse Preview-based Q-Learning Algorithm: Application to Highway Driving of Autonomous Vehicles](https://mlsanity.com/paper/2112.03232/) (2021)
- [Address Behaviour Vulnerabilities in the Next Generation of Autonomous Robots](https://mlsanity.com/paper/2103.13268/) (2021)
- [Simplification of Risk Averse POMDPs with Performance Guarantees](https://mlsanity.com/paper/2406.03000/) (2024)
- [Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees](https://mlsanity.com/paper/2609.35874/) (2026)

## Abstract (arXiv)

We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives. Synthesizing risk-averse optimal policies for POMDPs requires infinite memory and thus undecidable. To overcome this difficulty, we propose a method based on bounded policy iteration for designing stochastic but finite state (memory) controllers, which takes advantage of standard convex optimization methods. Given a memory budget and optimality criterion, the proposed method modifies the stochastic finite state controller leading to sub-optimal solutions with lower coherent risk.