Multi-agent RL with self-play trains quadrotors that beat a human champion at 22 m/s races while halving collisions versus single-agent methods and generalizing zero-shot to human opponents.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
Multi-agent RL with self-play trains quadrotors that beat a human champion at 22 m/s races while halving collisions versus single-agent methods and generalizing zero-shot to human opponents.