# Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations

arXiv: https://arxiv.org/abs/2308.03882 · HTML: https://mlsanity.com/paper/2308.03882/

## Key facts

- Cited by 2 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 16 of its 19 references that are in the map.
- First posted on arXiv 7 Aug 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, 16 of 16)

- [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)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [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)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning](https://mlsanity.com/paper/1803.00101/) (2018)
- [Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation](https://mlsanity.com/paper/1807.01473/) (2018)
- [A Workflow for Offline Model-Free Robotic Reinforcement Learning](https://mlsanity.com/paper/2109.10813/) (2021)
- [NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning](https://mlsanity.com/paper/2102.00714/) (2021)
- [How to Leverage Unlabeled Data in Offline Reinforcement Learning](https://mlsanity.com/paper/2202.01741/) (2022)
- [DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning](https://mlsanity.com/paper/2102.11492/) (2021)
- [Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation](https://mlsanity.com/paper/2106.15587/) (2021)
- [Revisiting Model-based Value Expansion](https://mlsanity.com/paper/2203.14660/) (2022)

## Built on by (most cited first, 2 of 2)

- [Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use](https://mlsanity.com/paper/2410.24218/) (2024)
- [LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning](https://mlsanity.com/paper/2509.00347/) (2025)

## Abstract (arXiv)

Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions, while model-based methods are able to further exploit unseen states via model rollouts. However, such methods are handicapped in their ability to find unseen states far away from the available offline data due to two factors -- (a) very short rollout horizons in models due to cascading model errors, and (b) model rollouts originating solely from states observed in offline data. We relax the second assumption and present a novel unseen state augmentation strategy to allow exploitation of unseen states where the learned model and value estimates generalize. Our strategy finds unseen states by value-informed perturbations of seen states followed by filtering out states with epistemic uncertainty estimates too high (high error) or too low (too similar to seen data). We observe improved performance in several offline RL tasks and find that our augmentation strategy consistently leads to overall lower average dataset Q-value estimates i.e. more conservative Q-value estimates than a baseline.