# Generalization in Reinforcement Learning by Soft Data Augmentation

arXiv: https://arxiv.org/abs/2011.13389 · HTML: https://mlsanity.com/paper/2011.13389/

## Key facts

- Cited by 137 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 30 of 137)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation](https://mlsanity.com/paper/2402.08191/) (2024)
- [ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation](https://mlsanity.com/paper/2403.08321/) (2024)
- [Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation](https://mlsanity.com/paper/2107.00644/) (2021)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation](https://mlsanity.com/paper/2504.13055/) (2025)
- [Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation](https://mlsanity.com/paper/2307.03659/) (2023)
- [Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers](https://mlsanity.com/paper/2107.03996/) (2021)
- [Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning](https://mlsanity.com/paper/2212.08860/) (2022)
- [TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning](https://mlsanity.com/paper/2306.13229/) (2023)
- [On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline](https://mlsanity.com/paper/2212.05749/) (2022)
- [Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models](https://mlsanity.com/paper/2205.13817/) (2022)
- [Learning Generalizable Dexterous Manipulation from Human Grasp Affordance](https://mlsanity.com/paper/2204.02320/) (2022)
- [Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation](https://mlsanity.com/paper/2201.07779/) (2022)
- [DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization](https://mlsanity.com/paper/2310.19668/) (2023)
- [Visual Reinforcement Learning with Self-Supervised 3D Representations](https://mlsanity.com/paper/2210.07241/) (2022)
- [Latent Action Learning Requires Supervision in the Presence of Distractors](https://mlsanity.com/paper/2502.00379/) (2025)
- [SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies](https://mlsanity.com/paper/2106.09678/) (2021)
- [Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning](https://mlsanity.com/paper/2407.15815/) (2024)
- [Mask-based Latent Reconstruction for Reinforcement Learning](https://mlsanity.com/paper/2201.12096/) (2022)
- [What Makes Pre-Trained Visual Representations Successful for Robust Manipulation?](https://mlsanity.com/paper/2312.12444/) (2023)
- [Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining](https://mlsanity.com/paper/2204.02393/) (2022)
- [Bootstrapped Transformer for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.08569/) (2022)
- [EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation](https://mlsanity.com/paper/2310.16050/) (2023)
- [Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability](https://mlsanity.com/paper/2209.08025/) (2022)
- [Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning](https://mlsanity.com/paper/2207.09081/) (2022)
- [Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning](https://mlsanity.com/paper/2209.09203/) (2022)

## Abstract (arXiv)

Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during training, optimization becomes increasingly challenging, and empirically may result in lower sample efficiency and unstable training. Instead of learning policies directly from augmented data, we propose SOft Data Augmentation (SODA), a method that decouples augmentation from policy learning. Specifically, SODA imposes a soft constraint on the encoder that aims to maximize the mutual information between latent representations of augmented and non-augmented data, while the RL optimization process uses strictly non-augmented data. Empirical evaluations are performed on diverse tasks from DeepMind Control suite as well as a robotic manipulation task, and we find SODA to significantly advance sample efficiency, generalization, and stability in training over state-of-the-art vision-based RL methods.