# Safe Policy Improvement with Baseline Bootstrapping

arXiv: https://arxiv.org/abs/1712.06924 · HTML: https://mlsanity.com/paper/1712.06924/

## Key facts

- Cited by 144 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2017.

## Built on by (most cited first, 30 of 144)

- [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)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [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)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism](https://mlsanity.com/paper/2103.12021/) (2021)
- [Bellman-consistent Pessimism for Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06926/) (2021)
- [Offline RL Without Off-Policy Evaluation](https://mlsanity.com/paper/2106.08909/) (2021)
- [What are the Statistical Limits of Offline RL with Linear Function Approximation?](https://mlsanity.com/paper/2010.11895/) (2020)
- [Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning](https://mlsanity.com/paper/2105.08140/) (2021)
- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation](https://mlsanity.com/paper/2106.10783/) (2021)
- [Benchmarking Batch Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/1910.01708/) (2019)
- [Adversarially Trained Actor Critic for Offline Reinforcement Learning](https://mlsanity.com/paper/2202.02446/) (2022)
- [Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning](https://mlsanity.com/paper/2108.08812/) (2021)
- [When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?](https://mlsanity.com/paper/2204.05618/) (2022)
- [Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.03400/) (2021)
- [Provably Good Batch Reinforcement Learning Without Great Exploration](https://mlsanity.com/paper/2007.08202/) (2020)
- [For SALE: State-Action Representation Learning for Deep Reinforcement Learning](https://mlsanity.com/paper/2306.02451/) (2023)
- [Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation](https://mlsanity.com/paper/2111.10919/) (2021)
- [COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation](https://mlsanity.com/paper/2204.08957/) (2022)
- [Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings](https://mlsanity.com/paper/2107.11003/) (2021)
- [Conservative Data Sharing for Multi-Task Offline Reinforcement Learning](https://mlsanity.com/paper/2109.08128/) (2021)
- [How to Leverage Unlabeled Data in Offline Reinforcement Learning](https://mlsanity.com/paper/2202.01741/) (2022)
- [RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.13888/) (2020)
- [Corruption-Robust Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06630/) (2021)
- [Offline Reinforcement Learning as Anti-Exploration](https://mlsanity.com/paper/2106.06431/) (2021)

## Abstract (arXiv)

This paper considers Safe Policy Improvement (SPI) in Batch Reinforcement Learning (Batch RL): from a fixed dataset and without direct access to the true environment, train a policy that is guaranteed to perform at least as well as the baseline policy used to collect the data. Our approach, called SPI with Baseline Bootstrapping (SPIBB), is inspired by the knows-what-it-knows paradigm: it bootstraps the trained policy with the baseline when the uncertainty is high. Our first algorithm, Pib-SPIBB, comes with SPI theoretical guarantees. We also implement a variant, Pi≤ b-SPIBB, that is even more efficient in practice. We apply our algorithms to a motivational stochastic gridworld domain and further demonstrate on randomly generated MDPs the superiority of SPIBB with respect to existing algorithms, not only in safety but also in mean performance. Finally, we implement a model-free version of SPIBB and show its benefits on a navigation task with deep RL implementation called SPIBB-DQN, which is, to the best of our knowledge, the first RL algorithm relying on a neural network representation able to train efficiently and reliably from batch data, without any interaction with the environment.