Year: 2015
Type: preprint
Abstract: We propose a distributed deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is based on the deep Q-network, a convolutional neural network trained with a variant of Q-learning. Its input is raw pixels and its output is a value function estimating future rewards from taking an action given a system state. To distribute the deep Q-network training, we adapt the DistBelief software framework to the context of efficiently training reinforcement learning agents. As a result, the method is completely asynchronous and scales well with the number of machines. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to achieve reasonable success on a simple game with minimal parameter tuning.
Source: arXiv (Cornell University)
Authors: Ong, Hao Yi, Chavez, Kevin, Hong, Augustus
Institution: Stanford University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1890963104