# Adaptive Tree Backup Algorithms for Temporal-Difference Reinforcement Learning

arXiv: https://arxiv.org/abs/2206.01896 · HTML: https://mlsanity.com/paper/2206.01896/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 10 references that are in the map.
- First posted on arXiv 4 Jun 2022.

## Builds on (most cited first, 1 of 1)

- [Multi-step Reinforcement Learning: A Unifying Algorithm](https://mlsanity.com/paper/1703.01327/) (2017)

## Abstract (arXiv)

Q(σ) is a recently proposed temporal-difference learning method that interpolates between learning from expected backups and sampled backups. It has been shown that intermediate values for the interpolation parameter σ ∈ [0,1] perform better in practice, and therefore it is commonly believed that σ functions as a bias-variance trade-off parameter to achieve these improvements. In our work, we disprove this notion, showing that the choice of σ=0 minimizes variance without increasing bias. This indicates that σ must have some other effect on learning that is not fully understood. As an alternative, we hypothesize the existence of a new trade-off: larger σ-values help overcome poor initializations of the value function, at the expense of higher statistical variance. To automatically balance these considerations, we propose Adaptive Tree Backup (ATB) methods, whose weighted backups evolve as the agent gains experience. Our experiments demonstrate that adaptive strategies can be more effective than relying on fixed or time-annealed σ-values.