A hierarchical quadruped controller uses online optimization over the low-level policy's value function to choose footstep targets, improving normalized reward and reducing collisions over an end-to-end baseline without additional training samples.
Policies modulating trajectory generators,
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
-
Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion
A hierarchical quadruped controller uses online optimization over the low-level policy's value function to choose footstep targets, improving normalized reward and reducing collisions over an end-to-end baseline without additional training samples.