AI Olympics challenge with Evolutionary Soft Actor Critic
This is an incremental approach for a specific robotics competition, with no broader impact described.
The authors tackled the AI Olympics competition at IROS 2024 by proposing a solution based on a model-free deep reinforcement learning approach combined with an evolutionary strategy, but no concrete results or numbers are provided in the 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