Reinforcement Learning for Solving Robotic Reaching Tasks in the Neurorobotics Platform

TL;DR

This paper explores reinforcement learning methods for robotic reaching tasks in the Neurorobotics Platform, demonstrating improved training efficiency through curriculum learning with both ground truth and image data inputs.

Contribution

It introduces a comparison of state-of-the-art RL algorithms for robotic reaching in simulation and shows how curriculum learning enhances training performance.

Findings

Training with ground truth data achieves rapid reaching.

Curriculum learning improves efficiency with image data.

Dynamic training schedules enhance overall results.

Abstract

In recent years, reinforcement learning (RL) has shown great potential for solving tasks in well-defined environments like games or robotics. This paper aims to solve the robotic reaching task in a simulation run on the Neurorobotics Platform (NRP). The target position is initialized randomly and the robot has 6 degrees of freedom. We compare the performance of various state-of-the-art model-free algorithms. At first, the agent is trained on ground truth data from the simulation to reach the target position in only one continuous movement. Later the complexity of the task is increased by using image data as input from the simulation environment. Experimental results show that training efficiency and results can be improved with appropriate dynamic training schedule function for curriculum learning.