A residual reinforcement learning controller trained entirely on a physical 1:10 race car beats a pursuit controller's lap time by up to 11.5% after about 20 minutes of on-track practice.
Hindsight Experience Replay
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Drive Fast, Learn Faster: On-Board RL for High Performance Autonomous Racing
A residual reinforcement learning controller trained entirely on a physical 1:10 race car beats a pursuit controller's lap time by up to 11.5% after about 20 minutes of on-track practice.