# Policy Learning for Off-Dynamics RL with Deficient Support

arXiv: https://arxiv.org/abs/2402.10765 · HTML: https://mlsanity.com/paper/2402.10765/

## Key facts

- Cited by 9 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 21 of its 42 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## 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, 21 of 21)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [CAD2RL: Real Single-Image Flight without a Single Real Image](https://mlsanity.com/paper/1611.04201/) (2016)
- [Preparing for the Unknown: Learning a Universal Policy with Online System Identification](https://mlsanity.com/paper/1702.02453/) (2017)
- [Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees](https://mlsanity.com/paper/1807.03858/) (2018)
- [Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers](https://mlsanity.com/paper/2006.13916/) (2020)
- [Improving Generalization in Reinforcement Learning with Mixture Regularization](https://mlsanity.com/paper/2010.10814/) (2020)
- [Off-policy Bandits with Deficient Support](https://mlsanity.com/paper/2006.09438/) (2020)
- [Cross-Domain Policy Adaptation via Value-Guided Data Filtering](https://mlsanity.com/paper/2305.17625/) (2023)
- [Reinforced Grounded Action Transformation for Sim-to-Real Transfer](https://mlsanity.com/paper/2008.01279/) (2020)
- [Stochastic Grounded Action Transformation for Robot Learning in Simulation](https://mlsanity.com/paper/2008.01281/) (2020)
- [Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation](https://mlsanity.com/paper/2106.15587/) (2021)
- [Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding](https://mlsanity.com/paper/2107.00339/) (2021)
- [Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support](https://mlsanity.com/paper/2107.11533/) (2021)
- [Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp](https://mlsanity.com/paper/2011.14487/) (2020)
- [Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks](https://mlsanity.com/paper/2205.09117/) (2022)

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

- [ODRL: A Benchmark for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.20750/) (2024)
- [DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning](https://mlsanity.com/paper/2507.20499/) (2025)
- [Hybrid Cross-domain Robust Reinforcement Learning](https://mlsanity.com/paper/2505.23003/) (2025)
- [A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation](https://mlsanity.com/paper/2503.05696/) (2025)
- [Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer](https://mlsanity.com/paper/2505.09114/) (2025)
- [Cross-Domain Offline Policy Adaptation via Selective Transition Correction](https://mlsanity.com/paper/2602.05776/) (2026)
- [DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects](https://mlsanity.com/paper/2505.00961/) (2025)
- [DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learning](https://mlsanity.com/paper/2607.16090/) (2026)
- [Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning](https://mlsanity.com/paper/2610.02505/) (2026)

## Abstract (arXiv)

Reinforcement Learning (RL) can effectively learn complex policies. However, learning these policies often demands extensive trial-and-error interactions with the environment. In many real-world scenarios, this approach is not practical due to the high costs of data collection and safety concerns. As a result, a common strategy is to transfer a policy trained in a low-cost, rapid source simulator to a real-world target environment. However, this process poses challenges. Simulators, no matter how advanced, cannot perfectly replicate the intricacies of the real world, leading to dynamics discrepancies between the source and target environments. Past research posited that the source domain must encompass all possible target transitions, a condition we term full support. However, expecting full support is often unrealistic, especially in scenarios where significant dynamics discrepancies arise. In this paper, our emphasis shifts to addressing large dynamics mismatch adaptation. We move away from the stringent full support condition of earlier research, focusing instead on crafting an effective policy for the target domain. Our proposed approach is simple but effective. It is anchored in the central concepts of the skewing and extension of source support towards target support to mitigate support deficiencies. Through comprehensive testing on a varied set of benchmarks, our method's efficacy stands out, showcasing notable improvements over previous techniques.