# Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning

arXiv: https://arxiv.org/abs/2103.14718 · HTML: https://mlsanity.com/paper/2103.14718/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction](https://mlsanity.com/paper/1910.05449/) (2019)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks](https://mlsanity.com/paper/1809.10732/) (2018)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [CoverNet: Multimodal Behavior Prediction using Trajectory Sets](https://mlsanity.com/paper/1911.10298/) (2019)
- [Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning](https://mlsanity.com/paper/2001.08726/) (2020)
- [Model-free Deep Reinforcement Learning for Urban Autonomous Driving](https://mlsanity.com/paper/1904.09503/) (2019)
- [Driving Policy Transfer via Modularity and Abstraction](https://mlsanity.com/paper/1804.09364/) (2018)
- [Urban Driving with Conditional Imitation Learning](https://mlsanity.com/paper/1912.00177/) (2019)
- [Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge](https://mlsanity.com/paper/1709.02066/) (2017)
- [Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations](https://mlsanity.com/paper/1909.06993/) (2019)
- [Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning](https://mlsanity.com/paper/1904.12374/) (2019)
- [Predicting Motion of Vulnerable Road Users using High-Definition Maps and Efficient ConvNets](https://mlsanity.com/paper/1906.08469/) (2019)
- [Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning](https://mlsanity.com/paper/1904.10171/) (2019)
- [Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions](https://mlsanity.com/paper/1908.00219/) (2019)

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

- [Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous Driving](https://mlsanity.com/paper/2208.12263/) (2022)
- [Dream to Drive with Predictive Individual World Model](https://mlsanity.com/paper/2501.16733/) (2025)
- [DeepIPCv2: LiDAR-powered Robust Environmental Perception and Navigational Control for Autonomous Vehicle](https://mlsanity.com/paper/2307.06647/) (2023)
- [A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective](https://mlsanity.com/paper/2503.23650/) (2025)
- [Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies](https://mlsanity.com/paper/2510.05692/) (2025)

## Abstract (arXiv)

Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level representations that encode a vehicle's environment as images have become a popular choice. Still, they are quite high-dimensional, limiting their use in data-hungry approaches such as reinforcement learning. In this article, we propose to learn a low-dimensional and rich latent representation of the environment by leveraging the knowledge of relevant semantic factors. To do this, we train an encoder-decoder deep neural network to predict multiple application-relevant factors such as the trajectories of other agents and the ego car. Furthermore, we propose a hazard signal based on other vehicles' future trajectories and the planned route which is used in conjunction with the learned latent representation as input to a down-stream policy. We demonstrate that using the multi-head encoder-decoder neural network results in a more informative representation than a standard single-head model. In particular, the proposed representation learning and the hazard signal help reinforcement learning to learn faster, with increased performance and less data than baseline methods.