# SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data

arXiv: https://arxiv.org/abs/2605.05863 · HTML: https://mlsanity.com/paper/2605.05863/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 24 of 24)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards](https://mlsanity.com/paper/1707.08817/) (2017)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient](https://mlsanity.com/paper/2210.06718/) (2022)
- [More Robust Doubly Robust Off-policy Evaluation](https://mlsanity.com/paper/1802.03493/) (2018)
- [Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1911.06854/) (2019)
- [Hyperparameter Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2007.09055/) (2020)
- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2110.14000/) (2021)
- [Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization](https://mlsanity.com/paper/2311.03351/) (2023)
- [Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse](https://mlsanity.com/paper/2305.18443/) (2023)
- [SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning](https://mlsanity.com/paper/2501.08669/) (2025)
- [Active Advantage-Aligned Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2502.07937/) (2025)
- [Reinforcement Learning for High-Level Strategic Control in Tower Defense Games](https://mlsanity.com/paper/2406.07980/) (2024)

## Built on by (most cited first, 1 of 1)

- [ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders](https://mlsanity.com/paper/2605.19503/) (2026)

## Abstract (arXiv)

Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases are significantly more computationally efficient than static update schedules, they require task-dependent manual tuning, risking either the waste of prior knowledge or severe overfitting. To address this, we propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation (OPE) signal as an automated early-stopping mechanism to dynamically control the length of offline training phases. By evaluating the critic on a held-out validation split under the current policy's action distribution, SOPE halts gradient updates exactly when out-of-distribution benefits saturate, eliminating the need for manual schedule tuning. Evaluated on 25 continuous control tasks from the Minari benchmark suite, SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x, thus balancing the tradeoff between sample and computational efficiency. These findings demonstrate that adaptive, evaluation-driven update schedules are more effective than relying on static, exhaustive update schedules.