238
click to vote
JMLR
2010
15 years 2 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...
229
Voted
ECML
2005
Springer
16 years 28 days ago
2005
Springer
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...