Filters








2 Hits in 6.6 sec

Approximate dynamic programming with Bézier Curves/Surfaces for Top-percentile Traffic Routing

Andreas Grothey, Xinan Yang
2012 European Journal of Operational Research  
doi:10.1016/j.ejor.2011.11.041 fatcat:x56ogu43tngxboghcmyqpa2lty

Parameter Space Abstractions for Diversity-based Policy Search

Nemanja Rakicevic, Petar Kormushev, Peter Childs
2022
In certain cases where the environment dynamics change dramatically, due to moving obstacles or partial agent damage, a single policy may not be sufficient.  ...  Therefore, maintaining a diversity of policies is necessary to provide alternatives for the system to function normally.  ...  Specifically, these representations are motivated by a geometric perspective of the policy as a curved surface of the policy distribution, and learned through contrastive learning and action prediction  ... 
doi:10.25560/96985 fatcat:wtx7usqrybavnkbvpbfsknq6xm