Timezone: »

Neural Episodic Control
Alexander Pritzel · Benigno Uria · Srinivasan Sriram · Adrià Puigdomenech Badia · Oriol Vinyals · Demis Hassabis · Daan Wierstra · Charles Blundell

Tue Aug 08 11:06 PM -- 11:24 PM (PDT) @ C4.5

Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose Neural Episodic Control: a deep reinforcement learning agent that is able to rapidly assimilate new experiences and act upon them. Our agent uses a semi-tabular representation of the value function: a buffer of past experience containing slowly changing state representations and rapidly updated estimates of the value function. We show across a wide range of environments that our agent learns significantly faster than other state-of-the-art, general purpose deep reinforcement learning agents.

Author Information

Alexander Pritzel (Deepmind)
Benigno Uria (Deepmind)
Raam Sriram (DeepMind)
Adrià Puigdomenech Badia (Deepmind)
Oriol Vinyals (DeepMind)

Oriol Vinyals is a Research Scientist at Google. He works in deep learning with the Google Brain team. Oriol holds a Ph.D. in EECS from University of California, Berkeley, and a Masters degree from University of California, San Diego. He is a recipient of the 2011 Microsoft Research PhD Fellowship. He was an early adopter of the new deep learning wave at Berkeley, and in his thesis he focused on non-convex optimization and recurrent neural networks. At Google Brain he continues working on his areas of interest, which include artificial intelligence, with particular emphasis on machine learning, language, and vision.

Demis Hassabis (Deepmind)
Daan Wierstra (Google DeepMind)
Charles Blundell (DeepMind)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors