# State Regularized Policy Optimization on Data with Dynamics Shift

arXiv: https://arxiv.org/abs/2306.03552 · HTML: https://mlsanity.com/paper/2306.03552/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 43)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [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)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [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)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections](https://mlsanity.com/paper/1906.04733/) (2019)
- [Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation](https://mlsanity.com/paper/1810.12429/) (2018)
- [VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning](https://mlsanity.com/paper/1910.08348/) (2019)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2005.06800/) (2020)
- [Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers](https://mlsanity.com/paper/2006.13916/) (2020)
- [Offline Meta-Reinforcement Learning with Advantage Weighting](https://mlsanity.com/paper/2008.06043/) (2020)
- [Error Bounds of Imitating Policies and Environments](https://mlsanity.com/paper/2010.11876/) (2020)
- [State Alignment-based Imitation Learning](https://mlsanity.com/paper/1911.10947/) (2019)
- [Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations](https://mlsanity.com/paper/1308.3513/) (2013)
- [f-IRL: Inverse Reinforcement Learning via State Marginal Matching](https://mlsanity.com/paper/2011.04709/) (2020)
- [When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning](https://mlsanity.com/paper/2206.13464/) (2022)

## Built on by (most cited first, 23 of 23)

- [ODRL: A Benchmark for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.20750/) (2024)
- [Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning](https://mlsanity.com/paper/2405.06192/) (2024)
- [Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation](https://mlsanity.com/paper/2411.09891/) (2024)
- [A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents](https://mlsanity.com/paper/2402.04580/) (2024)
- [Skill Expansion and Composition in Parameter Space](https://mlsanity.com/paper/2502.05932/) (2025)
- [Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.23450/) (2024)
- [xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing](https://mlsanity.com/paper/2409.08687/) (2024)
- [MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning](https://mlsanity.com/paper/2506.08460/) (2025)
- [DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning](https://mlsanity.com/paper/2507.20499/) (2025)
- [Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts](https://mlsanity.com/paper/2512.02486/) (2025)
- [AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems](https://mlsanity.com/paper/2310.03984/) (2023)
- [Offline Reinforcement Learning from Datasets with Structured Non-Stationarity](https://mlsanity.com/paper/2405.14114/) (2024)
- [OMPO: A Unified Framework for RL under Policy and Dynamics Shifts](https://mlsanity.com/paper/2405.19080/) (2024)
- [Offline Reinforcement Learning with Domain-Unlabeled Data](https://mlsanity.com/paper/2404.07465/) (2024)
- [Mitigating Distribution Shift in Model-based Offline RL via Shifts-aware Reward Learning](https://mlsanity.com/paper/2408.12830/) (2024)
- [Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering](https://mlsanity.com/paper/2512.02435/) (2025)
- [FineFT: Efficient and Risk-Aware Ensemble Reinforcement Learning for Futures Trading](https://mlsanity.com/paper/2512.23773/) (2025)
- [Cross-Domain Offline Policy Adaptation via Selective Transition Correction](https://mlsanity.com/paper/2602.05776/) (2026)
- [Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2503.06893/) (2025)
- [Target-Aligned Fusion for Decision-Sequence Learning under Dynamics Shift](https://mlsanity.com/paper/2511.09173/) (2025)
- [Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning](https://mlsanity.com/paper/2605.22376/) (2026)
- [Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets](https://mlsanity.com/paper/2605.24862/) (2026)
- [DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learning](https://mlsanity.com/paper/2607.16090/) (2026)

## Abstract (arXiv)

In many real-world scenarios, Reinforcement Learning (RL) algorithms are trained on data with dynamics shift, i.e., with different underlying environment dynamics. A majority of current methods address such issue by training context encoders to identify environment parameters. Data with dynamics shift are separated according to their environment parameters to train the corresponding policy. However, these methods can be sample inefficient as data are used textitad hoc, and policies trained for one dynamics cannot benefit from data collected in all other environments with different dynamics. In this paper, we find that in many environments with similar structures and different dynamics, optimal policies have similar stationary state distributions. We exploit such property and learn the stationary state distribution from data with dynamics shift for efficient data reuse. Such distribution is used to regularize the policy trained in a new environment, leading to the SRPO (State Regularized Policy Optimization) algorithm. To conduct theoretical analyses, the intuition of similar environment structures is characterized by the notion of homomorphous MDPs. We then demonstrate a lower-bound performance guarantee on policies regularized by the stationary state distribution. In practice, SRPO can be an add-on module to context-based algorithms in both online and offline RL settings. Experimental results show that SRPO can make several context-based algorithms far more data efficient and significantly improve their overall performance.