# Particle Value Functions

arXiv: https://arxiv.org/abs/1703.05820 · HTML: https://mlsanity.com/paper/1703.05820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2017.

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

- [Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning](https://mlsanity.com/paper/2106.01404/) (2021)
- [On Policy Evaluation Algorithms in Distributional Reinforcement Learning](https://mlsanity.com/paper/2407.14175/) (2024)

## Abstract (arXiv)

The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economics and control literature, we review the risk-sensitive value function that arises from an exponential utility and illustrate its effects on an example. This risk-sensitive value function is not always applicable to reinforcement learning problems, so we introduce the particle value function defined by a particle filter over the distributions of an agent's experience, which bounds the risk-sensitive one. We illustrate the benefit of the policy gradients of this objective in Cliffworld.