An overview of the action space for deep reinforcement learning

J Zhu, F Wu, J Zhao - Proceedings of the 2021 4th International …, 2021‏ - dl.acm.org
In recent years, deep reinforcement learning has been applied to tasks in the real world
gradually. Especially in the field of control, reinforcement learning has shown …

Smooth exploration for robotic reinforcement learning

A Raffin, J Kober, F Stulp - Conference on robot learning, 2022‏ - proceedings.mlr.press
Reinforcement learning (RL) enables robots to learn skills from interactions with the real
world. In practice, the unstructured step-based exploration used in Deep RL–often very …

Learning insertion primitives with discrete-continuous hybrid action space for robotic assembly tasks

X Zhang, S **, C Wang, X Zhu… - … conference on robotics …, 2022‏ - ieeexplore.ieee.org
This paper introduces a discrete-continuous action space to learn insertion primitives for
robotic assembly tasks. Primitives are sequences of elementary actions with certain exit …

Action decoupled SAC reinforcement learning with discrete-continuous hybrid action spaces

Y Xu, Y Wei, K Jiang, L Chen, D Wang, H Deng - Neurocomputing, 2023‏ - Elsevier
Abstract Most existing Deep Reinforcement Learning (DRL) algorithms solely apply to
discrete action or continuous action spaces. However, the agent often has both continuous …