AI Olympics challenge with Evolutionary Soft Actor Critic

TL;DR

This paper presents a novel approach for the AI Olympics challenge at IROS 2024, combining deep reinforcement learning with evolutionary strategies to improve performance in robotics tasks.

Contribution

It introduces a hybrid method that integrates model-free deep reinforcement learning with evolutionary algorithms for robotics competitions.

Findings

Demonstrated improved performance over baseline methods

Effective integration of RL and evolutionary strategies

Applicable to complex robotics tasks

Abstract

In the following report, we describe the solution we propose for the AI Olympics competition held at IROS 2024. Our solution is based on a Model-free Deep Reinforcement Learning approach combined with an evolutionary strategy. We will briefly describe the algorithms that have been used and then provide details of the approach