# Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

arXiv: https://arxiv.org/abs/1911.04384 · HTML: https://mlsanity.com/paper/1911.04384/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2019.

## Built on by (most cited first, 2 of 2)

- [Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality](https://mlsanity.com/paper/2102.11866/) (2021)
- [A Unified Off-Policy Evaluation Approach for General Value Function](https://mlsanity.com/paper/2107.02711/) (2021)

## Abstract (arXiv)

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. 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.