Reinforcement Learning and DQN – learning to play from pixels

Re:Reinforcement Learning and DQN – learning to play from pi... by white_oak8 on Thursday August 25, 2016 @01:18PM (#12360728)

Awesome read!

Given the Doom examples, another work to add to the list at the end is https://github.com/Ardavans/DSR. Extends the idea of successor representations introduced by Peter Dayan[1] in the 1990s to successor features using a deep neural net. The learning algorithm is demonstrated with Doom.

[1] http://www.gatsby.ucl.ac.uk/~dayan/papers/d93b.pdf

[ Parent | on HN ]

Re:Reinforcement Learning and DQN – learning to play from pi... by rubenfiszel on Thursday August 25, 2016 @01:30PM (#12360824)

Thank you. It seems very interesting. I will add it as a reference once I am done reading it :)

[ Parent | on HN ]