Provably Convergent Off-Policy Actor-Critic with Function Approximation
By Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson. 2019
8 citations recorded by the source corpus.
We present the first provably convergent off-policy actor-critic algorithm (COF-PAC) with function approximation in a two-timescale form. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained via Gradient Emphasis Learning (GEM), a novel combination of the key ideas of Gradient Temporal Difference Learning and Emphatic Temporal Difference Learning. With the help of the emphasis critic and the canonical value function critic, we show convergence for COF-PAC, where the critics are linear and the actor can be nonlinear.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Shangtong Zhang
- Bo Liu
- Shimon Whiteson
- Sergey Levine
- J. Urgen Schmidhuber
- Chongjie Zhang
- Wendelin Böhmer
- Jakob N. Foerster
In Computational Theory and Mathematics
- Shimon Whiteson
- Shangtong Zhang
- Bo Liu
- Nan Jiang
- Sergey Levine
- Jiawei Huang
- Fernando Fernández
- Javier García
In Statistical and Nonlinear Physics
Citations in the corpus
- GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values (2020, methodology): “Zhang et al. (2019) show that some density ratios can be interpreted as special emphasis (Sutton et al., 2016).”