Marginal Utility for Planning in Continuous or Large Discrete Action Spaces

NIPS 2020, 2020.

Cited by: 0|Views13
EI
Weibo:
In this paper we explore explicitly learning a candidate action generator by optimizing a novel objective, marginal utility

Abstract:

Sample-based planning is a powerful family of algorithms for generating intelligent behavior from a model of the environment. Generating good candidate actions is critical to the success of sample-based planners, particularly in continuous or large action spaces. Typically, candidate action generation exhausts the action space, uses dom...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments