# Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains

arXiv: https://arxiv.org/abs/1906.04556 · HTML: https://mlsanity.com/paper/1906.04556/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2019.

## Built on by (most cited first, 3 of 3)

- [Rethinking Population-assisted Off-policy Reinforcement Learning](https://mlsanity.com/paper/2305.02949/) (2023)
- [Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees](https://mlsanity.com/paper/2212.05237/) (2022)
- [Time-Varying Constraint-Aware Reinforcement Learning for Energy Storage Control](https://mlsanity.com/paper/2405.10536/) (2024)

## Abstract (arXiv)

In the context of learning deterministic policies in continuous domains, we revisit an approach, which was first proposed in Continuous Actor Critic Learning Automaton (CACLA) and later extended in Neural Fitted Actor Critic (NFAC). This approach is based on a policy update different from that of deterministic policy gradient (DPG). Previous work has observed its excellent performance empirically, but a theoretical justification is lacking. To fill this gap, we provide a theoretical explanation to motivate this unorthodox policy update by relating it to another update and making explicit the objective function of the latter. We furthermore discuss in depth the properties of these updates to get a deeper understanding of the overall approach. In addition, we extend it and propose a new trust region algorithm, Penalized NFAC (PeNFAC). Finally, we experimentally demonstrate in several classic control problems that it surpasses the state-of-the-art algorithms to learn deterministic policies.