Reinforcement Learning with Unsupervised Auxiliary Tasks Reinforcement Learning with Unsupervised Auxiliary Tasks
Paper summary They describe a version of reinforcement learning where the system also learns to solve some auxiliary tasks, which helps with the main objective. https://i.imgur.com/fmTVxvr.png In addition to normal Q-learning, which predicts the downstream reward, they have the system learning 1) a separate policy for maximally changing the pixels on the screen, 2) maximally activating units in a hidden layer, and 3) predicting the reward at the next step, using biased sampling. They show that this improves learning speed and performance on Atari games and Labyrinth (a Quake-like 3D game).
arxiv.org
arxiv-sanity.com
scholar.google.com
Reinforcement Learning with Unsupervised Auxiliary Tasks
Max Jaderberg and Volodymyr Mnih and Wojciech Marian Czarnecki and Tom Schaul and Joel Z Leibo and David Silver and Koray Kavukcuoglu
arXiv e-Print archive - 2016 via Local arXiv
Keywords: cs.LG, cs.NE

more

Summary by Denny Britz 1 year ago
Loading...
Your comment:
Summary by Marek Rei 6 months ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and