# Taylor Expansion Policy Optimization

arXiv: https://arxiv.org/abs/2003.06259 · HTML: https://mlsanity.com/paper/2003.06259/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [Offline Reinforcement Learning with Closed-Form Policy Improvement Operators](https://mlsanity.com/paper/2211.15956/) (2022)
- [Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation](https://mlsanity.com/paper/2106.13125/) (2021)
- [Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning](https://mlsanity.com/paper/2112.07328/) (2021)
- [Taylor Expansion of Discount Factors](https://mlsanity.com/paper/2106.06170/) (2021)
- [Reflective Policy Optimization](https://mlsanity.com/paper/2406.03678/) (2024)
- [Off-policy Distributional Q(λ): Distributional RL without Importance Sampling](https://mlsanity.com/paper/2402.05766/) (2024)
- [Taylor TD-learning](https://mlsanity.com/paper/2302.14182/) (2023)
- [DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm](https://mlsanity.com/paper/2305.18501/) (2023)
- [Symmetric Behavior Regularized Policy Optimization](https://mlsanity.com/paper/2508.04225/) (2025)

## Abstract (arXiv)

In this work, we investigate the application of Taylor expansions in reinforcement learning. In particular, we propose Taylor expansion policy optimization, a policy optimization formalism that generalizes prior work (e.g., TRPO) as a first-order special case. We also show that Taylor expansions intimately relate to off-policy evaluation. Finally, we show that this new formulation entails modifications which improve the performance of several state-of-the-art distributed algorithms.