|
Likelihood ratio policy gradient methods have been some of the most successful reinforcement learning algorithms, especially for learning on physical systems. We describe how the likelihood ratio policy gradient can be derived from an importance sampling perspective. This derivation highlights how likelihood ratio methods under-use past experience by (a) using the past experience to estimate the gradient of the expected return at the current policy parameterization, rather than to obtain a more complete estimate, and (b) using past experience under the current policy rather than using all past experience to improve the estimates. We present a new policy search method, which leverages both of these observations as well as generalized baselines - a new technique which generalizes commonly used baseline techniques for policy gradient methods. Our algorithm outperforms standard likelihood ratio policy gradient algorithms on several testbeds.
|
Video Length: 0
Date Found: March 26, 2011
Date Produced: March 25, 2011
|
|
VideoLectures |
July 10, 2011
The explosion in growth of the Web of Linked Data has provided, for the first time, a plethora of information in disparate locations, yet bound together by machine-readable, semantically typed relations. Utilisation of the Web of Data has been, until now, restricted to members of the community, ...
|
VideoLectures |
July 10, 2011
Problems cannot be solved with the mentality that has caused them’. Hence, the 2008- crisis cannot be solved with ethics of one-sided and short-term mentality of the industrial and neoliberal economics, which has caused the ‘Bubble Economy’ of several recent decades. Neither the market nor the ...
|
VideoLectures |
July 10, 2011
|
VideoLectures |
July 10, 2011
|
VideoLectures |
July 10, 2011
Social media presents unique challenges for topic classification, including the brevity of posts, the informal nature of conversations, and the frequent reliance on external hyperlinks to give context to a conversation. In this paper we investigate the usefulness of these external hyperlinks ...
|
|
|
|
|
|
Featured Content
Featuring websites that enhance the internet user’s experience.
|