Monthly Archives: March 2012

2nd JointMeeting 28.03.2012

Announcements: France is absent Progress: 1. Each student presents for two minutes his thesis topic and which problem he will tackle + how far he got to that goal. 2. Each student shows his results. 3. Each student tells what … Continue reading

Posted in Minutes | Leave a comment

Paper: Binary Action Search for Learning Continuous-Action Control Policies

NOTES -“Binary Action Search” BAS search the whole action range by increment and decrement the action-values for an “internal binary policy” -> what is that policy BAS eliminates restrictive modification steps of “Adaptive Action Modification” basement: – Least-Squares Policy Iteration … Continue reading

Posted in Paper | Leave a comment

Expanding in TLS

So far as I had understood expanding in TLS, it is restricted to the appearance of a split. Such that the selection/playout policy is to sample till a split appears and than expand the tree. When I talked to Colin … Continue reading

Posted in Thesis Progress | Leave a comment

Meeting 16.03.2012

Announcements Michael is apsent What has been done – implemented Colin’s interfaces (except for some details) – started to write about TLS – implemented a RSS-Value-based selection of tests (such that not the first sufficient test leads to a split, … Continue reading

Posted in Minutes | Leave a comment

Joint meeting 07.03.2012

(Joint meeting with all supervisors and students their thesis are related to TLS) Task:- “Describe what you have learned in that meeting” Colin: His topic focus on Holop and TLS. He will need to exchange several parts of the different … Continue reading

Posted in Minutes | Leave a comment