# Stability and Sensitivity Analysis of Relative Temporal-Difference Learning: Extended Version

arXiv: https://arxiv.org/abs/2603.27874 · HTML: https://mlsanity.com/paper/2603.27874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning](https://mlsanity.com/paper/1902.00923/) (2019)
- [Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation](https://mlsanity.com/paper/2207.04475/) (2022)
- [The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning](https://mlsanity.com/paper/2110.14427/) (2021)
- [Rates of Convergence in the Central Limit Theorem for Markov Chains, with an Application to TD Learning](https://mlsanity.com/paper/2401.15719/) (2024)
- [Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning](https://mlsanity.com/paper/2002.10301/) (2020)
- [Optimistic Training and Convergence of Q-Learning -- Extended Version](https://mlsanity.com/paper/2602.06146/) (2026)

## Abstract (arXiv)

Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied in the tabular setting, stability guarantees with function approximation remain poorly understood. This paper analyzes relative TD learning with linear function approximation. We establish stability conditions for the algorithm and show that the choice of baseline distribution plays a central role. In particular, when the baseline is chosen as the empirical distribution of the state-action process, the algorithm is stable for any non-negative baseline weight and any discount factor. We also provide a sensitivity analysis of the resulting parameter estimates, characterizing both asymptotic bias and covariance. The asymptotic covariance and asymptotic bias are shown to remain uniformly bounded as the discount factor approaches one.