# An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments

arXiv: https://arxiv.org/abs/1907.09466 · HTML: https://mlsanity.com/paper/1907.09466/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback](https://mlsanity.com/paper/2411.13410/) (2024)
- [Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras](https://mlsanity.com/paper/2404.14064/) (2024)
- [Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning](https://mlsanity.com/paper/2110.12985/) (2021)
- [Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning](https://mlsanity.com/paper/2102.10774/) (2021)
- [Discrete Control in Real-World Driving Environments using Deep Reinforcement Learning](https://mlsanity.com/paper/2211.15920/) (2022)

## Abstract (arXiv)

In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a deep reinforcement learning method and an attention mechanism in a multi-view environment. Each view can provide various representative information about the environment. Through our attention mechanism, our method generates a single feature representation of environment given its multiple views. It learns a policy to dynamically attend to each view based on its importance in the decision-making process. Through experiments, we show that our method outperforms its state-of-the-art baselines on TORCS racing car simulator and three other complex 3D environments with obstacles. We also provide experimental results to evaluate the performance of our method on noisy conditions and partial observation settings.