# K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning

arXiv: https://arxiv.org/abs/2604.23056 · HTML: https://mlsanity.com/paper/2604.23056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 9 of 9)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Deep Reinforcement Learning and the Deadly Triad](https://mlsanity.com/paper/1812.02648/) (2018)
- [Meta-Gradient Reinforcement Learning](https://mlsanity.com/paper/1805.09801/) (2018)
- [Multi-task Deep Reinforcement Learning with PopArt](https://mlsanity.com/paper/1809.04474/) (2018)
- [Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning](https://mlsanity.com/paper/2505.07527/) (2025)
- [Trust Region Value Optimization using Kalman Filtering](https://mlsanity.com/paper/1901.07860/) (2019)

## Abstract (arXiv)

We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for online reward estimation. Instead of relying on fixed heuristics, our method recursively estimates the latent reward mean, smoothing high-variance returns and adapting to non-stationary environments. This approach incurs minimal overhead and requires no modification to existing policy architectures. Experiments on textitLunarLander and textitCartPole demonstrate that Kalman-filtered rewards significantly accelerate convergence and reduce training variance compared to standard normalization techniques. Code is available at https://github.com/Sumxiaa/KalmanNormalization.