Universal Value Function Approximators

author: Tom Schaul, Google, Inc.
published: Dec. 5, 2015,   recorded: October 2015,   views: 2026
Categories

See Also:

Download slides icon Download slides: icml2015_schaul_universal_value_01.pdf (855.5 KB)


Help icon Streaming Video Help

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Bibliography

Description

Value functions are a core component of reinforcement learning. The main idea is to to construct a single function approximator V(s; theta) that estimates the long-term reward from any state s, using parameters θ. In this paper we introduce universal value function approximators (UVFAs) V(s,g;theta) that generalise not just over states s but also over goals g. We develop an efficient technique for supervised learning of UVFAs, by factoring observed values into separate embedding vectors for state and goal, and then learning a mapping from s and g to these factored embedding vectors. We show how this technique may be incorporated into a reinforcement learning algorithm that updates the UVFA solely from observed rewards. Finally, we demonstrate that a UVFA can successfully generalise to previously unseen goals.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: