Distributed Deep Q-Learning...... Hao Yi Ong,
Post# of 22465
Posted On: 08/22/2015 1:15:04 PM
Distributed Deep Q-Learning......
Hao Yi Ong, Kevin Chavez, Augustus Hong
(Submitted on 18 Aug 2015)
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.
http://arxiv.org/abs/1508.04186
Getting trippy now!!!!
Hao Yi Ong, Kevin Chavez, Augustus Hong
(Submitted on 18 Aug 2015)
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.
http://arxiv.org/abs/1508.04186
Getting trippy now!!!!
(0)
(0)