AI Olympics challenge with Evolutionary Soft Actor Critic

2024/09/02 by Calì, Marco, Sinigaglia, Alberto, Turcato, Niccolò +2 · 2 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2409.01104

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

Cited by

• VIMPPI: Enhancing Model Predictive Path Integral Control with Variational Integration for Underactuated Systems
• Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks

Related

• Velocity-History-Based Soft Actor-Critic Tackling IROS'24 Competition "AI Olympics with RealAIGym"
• Finetuning Deep Reinforcement Learning Policies with Evolutionary Strategies for Control of Underactuated Robots
• AI-Olympics: Exploring the Generalization of Agents through Open Competitions
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• The 2017 AIBIRDS Competition