# Bi-directional Value Learning for Risk-aware Planning Under Uncertainty: Extended Version

arXiv: https://arxiv.org/abs/1902.05698 · HTML: https://mlsanity.com/paper/1902.05698/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2019.

## Built on by (most cited first, 6 of 6)

- [NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge](https://mlsanity.com/paper/2103.11470/) (2021)
- [Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation](https://mlsanity.com/paper/2104.03111/) (2021)
- [LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty](https://mlsanity.com/paper/2209.11422/) (2022)
- [Risk-aware Meta-level Decision Making for Exploration Under Uncertainty](https://mlsanity.com/paper/2209.05580/) (2022)
- [Uncertainty Principles in Risk-Aware Statistical Estimation](https://mlsanity.com/paper/2104.14283/) (2021)
- [Risk-aware Integrated Task and Motion Planning for Versatile Snake Robots under Localization Failures](https://mlsanity.com/paper/2502.19690/) (2025)

## Abstract (arXiv)

Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be implicitly encoded as a value function. In partially observable settings, the value function is typically learned via forward simulation of the system evolution. Focusing on accurate and long-range risk assessment, we propose a novel method, where the value function is learned in different phases via a bi-directional search in belief space. A backward value learning process provides a long-range and risk-aware base policy. A forward value learning process ensures local optimality and updates the policy via forward simulations. We consider a class of scalable and continuous-space rover navigation problems (RNP) to assess the safety, scalability, and optimality of the proposed algorithm. The results demonstrate the capabilities of the proposed algorithm in evaluating long-range risk/safety of the planner while addressing continuous problems with long planning horizons.