# Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization

arXiv: https://arxiv.org/abs/1912.04078 · HTML: https://mlsanity.com/paper/1912.04078/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2019.

## Built on by (most cited first, 7 of 7)

- [Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge](https://mlsanity.com/paper/2109.09531/) (2021)
- [Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations](https://mlsanity.com/paper/2502.12530/) (2025)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [What Is Near?: Room Locality Learning for Enhanced Robot Vision-Language-Navigation in Indoor Living Environments](https://mlsanity.com/paper/2309.05036/) (2023)
- [Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2510.06277/) (2025)
- [Learning to Navigate from Scratch using World Models and Curiosity: the Good, the Bad, and the Ugly](https://mlsanity.com/paper/2308.15852/) (2023)
- [MAER-Nav: Bidirectional Motion Learning Through Mirror-Augmented Experience Replay for Robot Navigation](https://mlsanity.com/paper/2503.23908/) (2025)

## Abstract (arXiv)

To enhance the cross-target and cross-scene generalization of target-driven visual navigation based on deep reinforcement learning (RL), we introduce an information-theoretic regularization term into the RL objective. The regularization maximizes the mutual information between navigation actions and visual observation transforms of an agent, thus promoting more informed navigation decisions. This way, the agent models the action-observation dynamics by learning a variational generative model. Based on the model, the agent generates (imagines) the next observation from its current observation and navigation target. This way, the agent learns to understand the causality between navigation actions and the changes in its observations, which allows the agent to predict the next action for navigation by comparing the current and the imagined next observations. Cross-target and cross-scene evaluations on the AI2-THOR framework show that our method attains at least a 10% improvement of average success rate over some state-of-the-art models. We further evaluate our model in two real-world settings: navigation in unseen indoor scenes from a discrete Active Vision Dataset (AVD) and continuous real-world environments with a TurtleBot.We demonstrate that our navigation model is able to successfully achieve navigation tasks in these scenarios. Videos and models can be found in the supplementary material.