Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications

international conference on learning representations, 2019.

Cited by: 4|Views28
EI

Abstract:

Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over $mathbb{R}^d$ and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter. Such problems are naturally solved using po...More

Code:

Data:

Your rating :
0

 

Tags
Comments