Reinforcement Learning with A* and a Deep Heuristic
By Ariel Keselman, Sergey Ten, Adham Ghazali, Majed Jubeh. 2018
19 citations recorded by the source corpus.
A* is a popular path-finding algorithm, but it can only be applied to those domains where a good heuristic function is known. Inspired by recent methods combining Deep Neural Networks (DNNs) and trees, this study demonstrates how to train a heuristic represented by a DNN and combine it with A*. This new algorithm which we call aleph-star can be used efficiently in domains where the input to the heuristic could be processed by a neural network. We compare aleph-star to N-Step Deep Q-Learning (DQN Mnih et al. 2013) in a driving simulation with pixel-based input, and demonstrate significantly better performance in this scenario.
Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ibrahim Sobh
- B. R. Kiran
- Patrick Pérez
- Senthil Kumar Yogamani
- Ahmad A. Al Sallab
- Patrick Mannion
- Victor Talpaert
In Automotive Engineering
- Ibrahim Sobh
- B. R. Kiran
- Patrick Pérez
- Senthil Kumar Yogamani
- Ahmad A. Al Sallab
- Patrick Mannion
- Victor Talpaert
In Computer Vision and Pattern Recognition
- Senthil Kumar Yogamani
- Ibrahim Sobh
- Patrick Pérez
- Patrick Mannion
- Victor Talpaert
- Andrew Zisserman
- Luc Van Gool
- Xiaogang Wang
Citations in the corpus
- Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, methodology): “Authors propose to learn a heuristic function for the A∗ algorithm using a DQN over image-based input obstacle map [84] Overtaking Authors [85] propose Multi-goal RL (MGRL) framework to learn overtaking policy while avoiding collisions & maintain steady speed.”