Progressive extension of reinforcement learning action dimension for asymmetric assembly tasks

TL;DR

This paper introduces a progressive extension of action dimensions (PEAD) mechanism that accelerates reinforcement learning convergence in asymmetric assembly tasks by combining RL with compliance control, improving efficiency and stability.

Contribution

The paper proposes the novel PEAD mechanism to enhance RL convergence speed and efficiency specifically for complex asymmetric assembly tasks.

Findings

PEAD improves data-efficiency of RL algorithms.

PEAD accelerates convergence in RL.

PEAD increases stable rewards in RL applications.

Abstract

Reinforcement learning (RL) is always the preferred embodiment to construct the control strategy of complex tasks, like asymmetric assembly tasks. However, the convergence speed of reinforcement learning severely restricts its practical application. In this paper, the convergence is first accelerated by combining RL and compliance control. Then a completely innovative progressive extension of action dimension (PEAD) mechanism is proposed to optimize the convergence of RL algorithms. The PEAD method is verified in DDPG and PPO. The results demonstrate the PEAD method will enhance the data-efficiency and time-efficiency of RL algorithms as well as increase the stable reward, which provides more potential for the application of RL.