A non-episodic, model-based online optimizer, M-GAPS, tunes quadrotor and car controllers on hardware faster than episodic baselines and adapts to wind and payload changes.
Infinite-horizon policy-gradient estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Fast Non-Episodic Adaptive Tuning of Robot Controllers with Online Policy Optimization
A non-episodic, model-based online optimizer, M-GAPS, tunes quadrotor and car controllers on hardware faster than episodic baselines and adapts to wind and payload changes.