Discrete Action On-Policy Learning with Action-Value Critic

Yue Yuguang
Yue Yuguang
Tang Yunhao
Tang Yunhao
Yin Mingyuan
Yin Mingyuan

AISTATS, pp. 1977-1987, 2020.

Cited by: 0|Views38
EI

Abstract:

Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension, making it challenge to apply existing on-policy gradient based deep RL algorithms efficiently. To effectively operate in multidimensional discrete action spaces, we constr...More

Code:

Data:

Your rating :
0

 

Tags
Comments