# Fast Value Tracking for Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2403.13178 · HTML: https://mlsanity.com/paper/2403.13178/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## 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, 14 of 14)

- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis](https://mlsanity.com/paper/1702.03849/) (2017)
- [Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning](https://mlsanity.com/paper/1902.03932/) (2019)
- [A Complete Recipe for Stochastic Gradient MCMC](https://mlsanity.com/paper/1506.04696/) (2015)
- [Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks](https://mlsanity.com/paper/1512.07666/) (2015)
- [Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization](https://mlsanity.com/paper/1707.06618/) (2017)
- [Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1802.09756/) (2018)
- [On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators](https://mlsanity.com/paper/1610.06665/) (2016)
- [Consistent Sparse Deep Learning: Theory and Computation](https://mlsanity.com/paper/2102.13229/) (2021)
- [Kalman Temporal Differences](https://mlsanity.com/paper/1406.3270/) (2014)
- [Kalman meets Bellman: Improving Policy Evaluation through Value Tracking](https://mlsanity.com/paper/2002.07171/) (2020)
- [Approximate Kalman Filter Q-Learning for Continuous State-Space MDPs](https://mlsanity.com/paper/1309.6868/) (2013)
- [A Langevinized Ensemble Kalman Filter for Large-Scale Static and Dynamic Learning](https://mlsanity.com/paper/2105.05363/) (2021)

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

- [LoKO: Low-Rank Kalman Optimizer for Online Fine-Tuning of Large Models](https://mlsanity.com/paper/2410.11551/) (2024)
- [Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering](https://mlsanity.com/paper/2511.01694/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model parameters to maximize expected rewards, neglecting the stochastic dynamics of agent-environment interactions and the critical role of uncertainty quantification. Our research leverages the Kalman filtering paradigm to introduce a novel and scalable sampling algorithm called Langevinized Kalman Temporal-Difference (LKTD) for deep reinforcement learning. This algorithm, grounded in Stochastic Gradient Markov Chain Monte Carlo (SGMCMC), efficiently draws samples from the posterior distribution of deep neural network parameters. Under mild conditions, we prove that the posterior samples generated by the LKTD algorithm converge to a stationary distribution. This convergence not only enables us to quantify uncertainties associated with the value function and model parameters but also allows us to monitor these uncertainties during policy updates throughout the training phase. The LKTD algorithm paves the way for more robust and adaptable reinforcement learning approaches.