Policy Search In Continuous Action Domains: An Overview

Abstract

Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary algorithms. In this paper, we present a broad survey of policy search methods, providing a unified perspective on very different approaches, including also Bayesian Optimization and directed exploration methods. The main message of this overview is in the relationship between the families of methods, but we also outline some factors underlying sample efficiency properties of the various approaches.

Stats

• citations49
• S2 citations—
• github stars0
• HF likes0
• heat score12.74
• arxiv keysigaud2018policy

Related papers

• On The Sample Complexity And Metastability Of Heavy-tailed Policy Search In Continuous Control (2021)0.00
• Comparing Deep Reinforcement Learning And Evolutionary Methods In Continuous Control (2017)0.00
• CEM-RL: Combining Evolutionary And Gradient-based Methods For Policy Search (2018)0.00
• Extremum-seeking Action Selection For Accelerating Policy Optimization (2024)0.00
• Policy Optimization In A Noisy Neighborhood: On Return Landscapes In Continuous Control (2023)0.00
• Combining Evolution And Deep Reinforcement Learning For Policy Search: A Survey (2022)12.25
• Unified Policy Optimization For Continuous-action Reinforcement Learning In Non-stationary Tasks And Games (2022)2.26
• Exploiting The Sign Of The Advantage Function To Learn Deterministic Policies In Continuous Domains (2019)6.34