# Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning

arXiv: https://arxiv.org/abs/2502.08336 · HTML: https://mlsanity.com/paper/2502.08336/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 26 of 26)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Generalization in Reinforcement Learning by Soft Data Augmentation](https://mlsanity.com/paper/2011.13389/) (2020)
- [Self-Supervised Policy Adaptation during Deployment](https://mlsanity.com/paper/2007.04309/) (2020)
- [Phasic Policy Gradient](https://mlsanity.com/paper/2009.04416/) (2020)
- [Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation](https://mlsanity.com/paper/2107.00644/) (2021)
- [Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1910.05396/) (2019)
- [Decoupling Value and Policy for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2102.10330/) (2021)
- [Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning](https://mlsanity.com/paper/2212.08860/) (2022)
- [Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models](https://mlsanity.com/paper/2205.13817/) (2022)
- [Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation](https://mlsanity.com/paper/2201.07779/) (2022)
- [SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies](https://mlsanity.com/paper/2106.09678/) (2021)
- [Deep Reinforcement Learning based Automatic Exploration for Navigation in Unknown Environment](https://mlsanity.com/paper/2007.11808/) (2020)
- [Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning](https://mlsanity.com/paper/2209.09203/) (2022)
- [Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?](https://mlsanity.com/paper/2206.05266/) (2022)
- [Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning](https://mlsanity.com/paper/2202.09982/) (2022)
- [Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning](https://mlsanity.com/paper/2207.05480/) (2022)
- [Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation](https://mlsanity.com/paper/2308.01194/) (2023)
- [Rethinking Value Function Learning for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2210.09960/) (2022)

## Built on by (most cited first, 1 of 1)

- [What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models](https://mlsanity.com/paper/2605.13105/) (2026)

## Abstract (arXiv)

Generalizing policies to unseen scenarios remains a critical challenge in visual reinforcement learning, where agents often overfit to the specific visual observations of the training environment. In unseen environments, distracting pixels may lead agents to extract representations containing task-irrelevant information. As a result, agents may deviate from the optimal behaviors learned during training, thereby hindering visual generalization.To address this issue, we propose the Salience-Invariant Consistent Policy Learning (SCPL) algorithm, an efficient framework for zero-shot generalization. Our approach introduces a novel value consistency module alongside a dynamics module to effectively capture task-relevant representations. The value consistency module, guided by saliency, ensures the agent focuses on task-relevant pixels in both original and perturbed observations, while the dynamics module uses augmented data to help the encoder capture dynamic- and reward-relevant representations. Additionally, our theoretical analysis highlights the importance of policy consistency for generalization. To strengthen this, we introduce a policy consistency module with a KL divergence constraint to maintain consistent policies across original and perturbed observations.Extensive experiments on the DMC-GB, Robotic Manipulation, and CARLA benchmarks demonstrate that SCPL significantly outperforms state-of-the-art methods in terms of generalization. Notably, SCPL achieves average performance improvements of 14%, 39%, and 69% in the challenging DMC video hard setting, the Robotic hard setting, and the CARLA benchmark, respectively.Project Page: https://sites.google.com/view/scpl-rl.