# Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function

arXiv: https://arxiv.org/abs/2601.20554 · HTML: https://mlsanity.com/paper/2601.20554/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach](https://mlsanity.com/paper/1506.02188/) (2015)
- [Algorithms for CVaR Optimization in MDPs](https://mlsanity.com/paper/1406.3339/) (2014)
- [Online algorithms for POMDPs with continuous state, action, and observation spaces](https://mlsanity.com/paper/1709.06196/) (2017)
- [How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics](https://mlsanity.com/paper/1710.11040/) (2017)
- [Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path](https://mlsanity.com/paper/2206.02678/) (2022)
- [Optimality Guarantees for Particle Belief Approximation of POMDPs](https://mlsanity.com/paper/2210.05015/) (2022)
- [Risk-Averse Planning Under Uncertainty](https://mlsanity.com/paper/1909.12499/) (2019)

## Built on by (most cited first, 2 of 2)

- [POMDPPlanners: Open-Source Package for POMDP Planning](https://mlsanity.com/paper/2602.20810/) (2026)
- [Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees](https://mlsanity.com/paper/2609.35874/) (2026)

## Abstract (arXiv)

We study risk-sensitive planning under partial observability using the dynamic risk measure Iterated Conditional Value-at-Risk (ICVaR). A policy evaluation algorithm for ICVaR is developed with finite-time performance guarantees that do not depend on the cardinality of the action space. Building on this foundation, three widely used online planning algorithms--Sparse Sampling, Particle Filter Trees with Double Progressive Widening (PFT-DPW), and Partially Observable Monte Carlo Planning with Observation Widening (POMCPOW)--are extended to optimize the ICVaR value function rather than the expectation of the return. Our formulations introduce a risk parameter α, where α = 1 recovers standard expectation-based planning and α < 1 induces increasing risk aversion. For ICVaR Sparse Sampling, we establish finite-time performance guarantees under the risk-sensitive objective, which further enable a novel exploration strategy tailored to ICVaR. Experiments on benchmark POMDP domains demonstrate that the proposed ICVaR planners achieve lower tail risk compared to their risk-neutral counterparts.