Reinforcement Learning with A* and a Deep Heuristic

Code

• github.com/imagry/aleph_star
  OfficialIn paperpytorch★ 0
• github.com/bjotho/Zelda1AI
  none★ 0

Abstract

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.

Tasks

Reproductions