English

AI Olympics challenge with Evolutionary Soft Actor Critic

Robotics 2024-10-29 v2 Artificial Intelligence Machine Learning Neural and Evolutionary Computing

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

Cite

@article{arxiv.2409.01104,
  title  = {AI Olympics challenge with Evolutionary Soft Actor Critic},
  author = {Marco Calì and Alberto Sinigaglia and Niccolò Turcato and Ruggero Carli and Gian Antonio Susto},
  journal= {arXiv preprint arXiv:2409.01104},
  year   = {2024}
}

Comments

Added Sec 9 after testing on real robot

R2 v1 2026-06-28T18:31:15.046Z