blueeyes44
Re:Human in A.I. Loop
on Saturday September 10, 2016 @09:57AM (#12469201)
we wanted flying cars - instead we got tagged couture.
Re:Reinforcement Learning and DQN – learning to play from pixels
on Thursday August 25, 2016 @01:39PM (#12360909)
Couple key points: This project[0] is going to keep developing. It has Deep Q Learning now, A3C[1] is working and more features are being added.
Just as important: RL4J and DL4J run on a scientific computing framework called ND4J[2] that integrates with Spark and trains on multiple GPUs.[3][4]
It's basically porting RL to the production stack of large organizations that work with the JVM and need to scale.
The key thing to remember is that RL combines with other algorithms, like deep convolutional nets or Monte Carlo Search Trees. DL4J has the ConvNets already.[5]
[0] https://github.com/deeplearning4j/rl4j
[1] https://arxiv.org/abs/1602.01783
[2] http://nd4j.org/
[3] http://deeplearning4j.org/spark