Applies DDPG with a composite reward (attractive destination field, repulsive obstacle fields, control energy penalty) to learn safe paths, claiming faster real-time performance than pseudo-spectral optimal control in simulations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning Approach
Applies DDPG with a composite reward (attractive destination field, repulsive obstacle fields, control energy penalty) to learn safe paths, claiming faster real-time performance than pseudo-spectral optimal control in simulations.