# Risk-aware Stochastic Shortest Path

arXiv: https://arxiv.org/abs/2203.01640 · HTML: https://mlsanity.com/paper/2203.01640/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 3 Mar 2022.

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

- [Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach](https://mlsanity.com/paper/1506.02188/) (2015)
- [Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy](https://mlsanity.com/paper/1911.01546/) (2019)
- [Risk Aversion in Finite Markov Decision Processes Using Total Cost Criteria and Average Value at Risk](https://mlsanity.com/paper/1602.05130/) (2016)
- [On the Complexity of Value Iteration](https://mlsanity.com/paper/1807.04920/) (2018)
- [Conditional Value-at-Risk for Reachability and Mean Payoff in Markov Decision Processes](https://mlsanity.com/paper/1805.02946/) (2018)
- [Unifying Two Views on Multiple Mean-Payoff Objectives in Markov Decision Processes](https://mlsanity.com/paper/1502.00611/) (2015)

## Built on by (most cited first, 4 of 4)

- [Risk-averse Total-reward MDPs with ERM and EVaR](https://mlsanity.com/paper/2408.17286/) (2024)
- [Stopping Criteria for Value Iteration on Stochastic Games with Quantitative Objectives](https://mlsanity.com/paper/2304.09930/) (2023)
- [Forward-PECVaR Algorithm: Exact Evaluation for CVaR SSPs](https://mlsanity.com/paper/2303.00672/) (2023)
- [Risk-Averse Total-Reward Reinforcement Learning](https://mlsanity.com/paper/2506.21683/) (2025)

## Abstract (arXiv)

We treat the problem of risk-aware control for stochastic shortest path (SSP) on Markov decision processes (MDP). Typically, expectation is considered for SSP, which however is oblivious to the incurred risk. We present an alternative view, instead optimizing conditional value-at-risk (CVaR), an established risk measure. We treat both Markov chains as well as MDP and introduce, through novel insights, two algorithms, based on linear programming and value iteration, respectively. Both algorithms offer precise and provably correct solutions. Evaluation of our prototype implementation shows that risk-aware control is feasible on several moderately sized models.