TERL minimizes an estimated upper bound on action-trajectory entropy, producing more periodic and more robust locomotion policies in simulation.
Predictive modeling of periodic behavior for human-robot symbiotic walking,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Trajectory Entropy Reinforcement Learning for Predictable and Robust Control
TERL minimizes an estimated upper bound on action-trajectory entropy, producing more periodic and more robust locomotion policies in simulation.