# Extremum-Seeking Action Selection for Accelerating Policy Optimization

arXiv: https://arxiv.org/abs/2404.01598 · HTML: https://mlsanity.com/paper/2404.01598/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 26 of 26)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Noisy Networks for Exploration](https://mlsanity.com/paper/1706.10295/) (2017)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO](https://mlsanity.com/paper/2005.12729/) (2020)
- [MAVEN: Multi-Agent Variational Exploration](https://mlsanity.com/paper/1910.07483/) (2019)
- [Parameter Space Noise for Exploration](https://mlsanity.com/paper/1706.01905/) (2017)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping](https://mlsanity.com/paper/2011.02669/) (2020)
- [Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents](https://mlsanity.com/paper/1712.06560/) (2017)
- [Deep Drone Acrobatics](https://mlsanity.com/paper/2006.05768/) (2020)
- [A Survey of Exploration Methods in Reinforcement Learning](https://mlsanity.com/paper/2109.00157/) (2021)
- [Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity](https://mlsanity.com/paper/2210.09579/) (2022)
- [Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems](https://mlsanity.com/paper/2103.04490/) (2021)
- [Revisiting Design Choices in Proximal Policy Optimization](https://mlsanity.com/paper/2009.10897/) (2020)
- [Iterative Reachability Estimation for Safe Reinforcement Learning](https://mlsanity.com/paper/2309.13528/) (2023)
- [Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics](https://mlsanity.com/paper/2107.04989/) (2021)
- [Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning](https://mlsanity.com/paper/2305.14154/) (2023)
- [Dual Policy Iteration](https://mlsanity.com/paper/1805.10755/) (2018)
- [Online Algorithms and Policies Using Adaptive and Machine Learning Approaches](https://mlsanity.com/paper/2105.06577/) (2021)

## Built on by (most cited first, 1 of 1)

- [Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2610.18808/) (2026)

## Abstract (arXiv)

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control problems deal with complex unstable dynamics, where applying actions that are off the feasible control manifolds can quickly lead to undesirable divergence. In such cases, most samples taken from the ambient action space generate low-value trajectories that hardly contribute to policy improvement, resulting in slow or failed learning. We propose to improve action selection in this model-free RL setting by introducing additional adaptive control steps based on Extremum-Seeking Control (ESC). On each action sampled from stochastic policies, we apply sinusoidal perturbations and query for estimated Q-values as the response signal. Based on ESC, we then dynamically improve the sampled actions to be closer to nearby optima before applying them to the environment. Our methods can be easily added in standard policy optimization to improve learning efficiency, which we demonstrate in various control learning environments.