Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty

TL;DR

This paper introduces Dense2Sparse, a reward shaping method for deep reinforcement learning in robot manipulation, balancing learning speed and robustness to system uncertainty.

Contribution

The study proposes a novel reward shaping technique that combines dense and sparse rewards to improve learning efficiency and effectiveness under system uncertainty.

Findings

Dense2Sparse outperforms standalone dense or sparse rewards in expected reward.

The method demonstrates higher tolerance to system uncertainty.

Experimental results confirm faster convergence and robustness.

Abstract

Efficient and effective learning is one of the ultimate goals of the deep reinforcement learning (DRL), although the compromise has been made in most of the time, especially for the application of robot manipulations. Learning is always expensive for robot manipulation tasks and the learning effectiveness could be affected by the system uncertainty. In order to solve above challenges, in this study, we proposed a simple but powerful reward shaping method, namely Dense2Sparse. It combines the advantage of fast convergence of dense reward and the noise isolation of the sparse reward, to achieve a balance between learning efficiency and effectiveness, which makes it suitable for robot manipulation tasks. We evaluated our Dense2Sparse method with a series of ablation experiments using the state representation model with system uncertainty. The experiment results show that the Dense2Sparse method obtained higher expected reward compared with the ones using standalone dense reward or sparse reward, and it also has a superior tolerance of system uncertainty.