Distributed Deep Q-Learning
By Hao Yi Ong, Kevin Chavez, Augustus Hong. 2015
74 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Reinforcement Learning
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
In Computer Vision and Pattern Recognition
In Reinforcement Learning
Citations in the corpus
- Mobility-Aware Edge Caching and Computing in Vehicle Networks: A Deep Reinforcement Learning (2018, methodology): “3) We develop the algorithm based on deep Q-learning with multi-timescale framework [33]–[36] to configure the parameters of caching placement and computing resource allocation as well as to determine the sets of possible connecting RSUs and neighboring vehicles.”
- Integrated Networking, Caching, and Computing for Connected Vehicles: A Deep Reinforcement Learning Approach (2018, background): “Decision Process (MDP), however, state space, explicit transition probability and reward function are not necessarily required [32].”