Poster
Strategic Attentive Writer for Learning Macro-Actions
Alexander (Sasha) Vezhnevets · Volodymyr Mnih · Simon Osindero · Alex Graves · Oriol Vinyals · John Agapiou · koray kavukcuoglu

Mon Dec 5th 06:00 -- 09:30 PM @ Area 5+6+7+8 #111 #None
in Monday Posters »

We present a novel deep recurrent neural network architecture that learns to build implicit plans in an end-to-end manner purely by interacting with an environment in reinforcement learning setting. The network builds an internal plan, which is continuously updated upon observation of the next input from the environment. It can also partition this internal representation into contiguous sub-sequences by learning for how long the plan can be committed to -- i.e. followed without replaning. Combining these properties, the proposed model, dubbed STRategic Attentive Writer (STRAW) can learn high-level, temporally abstracted macro-actions of varying lengths that are solely learnt from data without any prior information. These macro-actions enable both structured exploration and economic computation. We experimentally demonstrate that STRAW delivers strong improvements on several ATARI games by employing temporally extended planning strategies (e.g. Ms. Pacman and Frostbite). It is at the same time a general algorithm that can be applied on any sequence data. To that end, we also show that when trained on text prediction task, STRAW naturally predicts frequent n-grams (instead of macro-actions), demonstrating the generality of the approach.

Keywords: Deep Learning or Neural Networks · Reinforcement Learning Algorithms

Author Information

Alexander Vezhnevets (Google DeepMind)
Volodymyr Mnih (DeepMind)
Simon Osindero (Google DeepMind)
Alex Graves (Google DeepMind)

Main contributions to neural networks include the Connectionist Temporal Classification training algorithm (widely used for speech, handwriting and gesture recognition, e.g. by Google voice search), a type of differentiable attention for RNNs (originally for handwriting generation, now a standard tool in computer vision, machine translation and elsewhere), stochastic gradient variational inference, and Neural Turing Machines. He works at Google Deep Mind.

Oriol Vinyals (Google 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.

John Agapiou (Google DeepMind)
koray kavukcuoglu (Google DeepMind)

More from the Same Authors