Abstract | ||
---|---|---|
In multi-robot reinforcement learning the goal is to enable a team of robots to learn a coordinated behavior from direct interaction with the environment. Here, we provide a comparison of the two main approaches to tackle this challenge, namely independent learners (IL) and joint-action learners (JAL). IL is suitable for highly scalable domains, but it faces non-stationarity issues. Whereas, JAL overcomes non-stationarity and can generate highly coordinated behaviors, but it presents scalability issues due to the increased size of the search space. We implement and evaluate these methods in a new multi-robot cooperative and adversarial soccer scenario, called 2 versus 2 free-kick task, where scalability issues affecting JAL are less relevant given the small number of learners. In this work, we implement and deploy these methodologies on a team of simulated NAO humanoid robots. We describe the implementation details of our scenario and show that both approaches are able to achieve satisfying solutions. Notably, we observe joint-action learners to have a better performance than independent learners in terms of success rate and quality of the learned policies. Finally, we discuss the results and provide conclusions based on our findings. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-35699-6_4 | RoboCup |
Field | DocType | Citations |
Computer science,Simulation,Human–computer interaction,Robot,Reinforcement learning,Humanoid robot,Scalability,Adversarial system | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jim Martin Catacora Ocana | 1 | 0 | 0.34 |
Francesco Riccio | 2 | 6 | 6.28 |
Roberto Capobianco | 3 | 40 | 9.78 |
Daniele Nardi | 4 | 5968 | 545.67 |