# Conservative State Value Estimation for Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2302.06884 · HTML: https://mlsanity.com/paper/2302.06884/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 14 Feb 2023.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 30 of 30)

- [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)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [Offline Reinforcement Learning with Fisher Divergence Critic Regularization](https://mlsanity.com/paper/2103.08050/) (2021)
- [Safe Policy Improvement with Baseline Bootstrapping](https://mlsanity.com/paper/1712.06924/) (2017)
- [Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning](https://mlsanity.com/paper/2105.08140/) (2021)
- [Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning](https://mlsanity.com/paper/2202.11566/) (2022)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [The Importance of Pessimism in Fixed-Dataset Policy Optimization](https://mlsanity.com/paper/2009.06799/) (2020)
- [Off-Policy Evaluation via the Regularized Lagrangian](https://mlsanity.com/paper/2007.03438/) (2020)
- [Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity](https://mlsanity.com/paper/2202.13890/) (2022)
- [d3rlpy: An Offline Deep Reinforcement Learning Library](https://mlsanity.com/paper/2111.03788/) (2021)
- [CoinDICE: Off-Policy Confidence Interval Estimation](https://mlsanity.com/paper/2010.11652/) (2020)
- [The Difficulty of Passive Learning in Deep Reinforcement Learning](https://mlsanity.com/paper/2110.14020/) (2021)
- [Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift](https://mlsanity.com/paper/1901.09455/) (2019)

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

- [Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model](https://mlsanity.com/paper/2410.20312/) (2024)
- [Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2406.08238/) (2024)
- [Imagination-Limited Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2505.12211/) (2025)
- [Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning](https://mlsanity.com/paper/2508.05960/) (2025)
- [Guardian: Decoupling Exploration from Safety in Reinforcement Learning](https://mlsanity.com/paper/2510.22859/) (2025)
- [A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic](https://mlsanity.com/paper/2603.28971/) (2026)
- [When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning](https://mlsanity.com/paper/2604.22873/) (2026)
- [Peng's Q(λ) for Conservative Value Estimation in Offline Reinforcement Learning](https://mlsanity.com/paper/2605.14779/) (2026)
- [Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation](https://mlsanity.com/paper/2609.19414/) (2026)

## Abstract (arXiv)

Offline reinforcement learning faces a significant challenge of value over-estimation due to the distributional drift between the dataset and the current learned policy, leading to learning failure in practice. The common approach is to incorporate a penalty term to reward or value estimation in the Bellman iterations. Meanwhile, to avoid extrapolation on out-of-distribution (OOD) states and actions, existing methods focus on conservative Q-function estimation. In this paper, we propose Conservative State Value Estimation (CSVE), a new approach that learns conservative V-function via directly imposing penalty on OOD states. Compared to prior work, CSVE allows more effective state value estimation with conservative guarantees and further better policy optimization. Further, we apply CSVE and develop a practical actor-critic algorithm in which the critic does the conservative value estimation by additionally sampling and penalizing the states around the dataset, and the actor applies advantage weighted updates extended with state exploration to improve the policy. We evaluate in classic continual control tasks of D4RL, showing that our method performs better than the conservative Q-function learning methods and is strongly competitive among recent SOTA methods.