Stimulate the Potential of Robots via Competition
This addresses the challenge of enhancing robot dynamics and learning efficiency in multiagent scenarios, though it appears incremental as it builds on existing competitive learning concepts.
The paper tackles the problem of improving robot performance by introducing a competitive learning framework that uses competition information as an auxiliary signal to learn advantaged actions, resulting in robots trained in competitive environments outperforming those trained with state-of-the-art algorithms in single-robot environments.
It is common for us to feel pressure in a competition environment, which arises from the desire to obtain success comparing with other individuals or opponents. Although we might get anxious under the pressure, it could also be a drive for us to stimulate our potentials to the best in order to keep up with others. Inspired by this, we propose a competitive learning framework which is able to help individual robot to acquire knowledge from the competition, fully stimulating its dynamics potential in the race. Specifically, the competition information among competitors is introduced as the additional auxiliary signal to learn advantaged actions. We further build a Multiagent-Race environment, and extensive experiments are conducted, demonstrating that robots trained in competitive environments outperform ones that are trained with SoTA algorithms in single robot environment.