CaR trains robots by maximizing a weighted sum of constraint functions with weights set by Lagrange multipliers, and it successfully taught a six-wheeled telescopic-legged robot to stand up from varied poses.
Robot parkour learning,
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
-
Constraints as Rewards: Reinforcement Learning for Robots without Reward Functions
CaR trains robots by maximizing a weighted sum of constraint functions with weights set by Lagrange multipliers, and it successfully taught a six-wheeled telescopic-legged robot to stand up from varied poses.