# Combining Deep Reinforcement Learning And Local Control For The Acrobot Swing-up And Balance Task

arXiv: https://arxiv.org/abs/2012.11663 · HTML: https://mlsanity.com/paper/2012.11663/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations](https://mlsanity.com/paper/2203.02857/) (2022)
- [Enhancing Reinforcement Learning Agents with Local Guides](https://mlsanity.com/paper/2402.13930/) (2024)
- [Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark](https://mlsanity.com/paper/2402.13654/) (2024)
- [Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies](https://mlsanity.com/paper/2109.05604/) (2021)
- [Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings](https://mlsanity.com/paper/2610.03065/) (2026)

## Abstract (arXiv)

In this work we present a novel extension of soft actor critic, a state of the art deep reinforcement algorithm. Our method allows us to combine traditional controllers with learned neural network policies. This combination allows us to leverage both our own domain knowledge and some of the advantages of model free reinforcement learning. We demonstrate our algorithm by combining a hand designed linear quadratic regulator with a learned controller for the acrobot problem. We show that our technique outperforms other state of the art reinforcement learning algorithms in this setting.