A neural network's predicted guideline and region are used as a reward function and Q-table initializer, cutting Q-learning convergence steps by about 90% in grid path planning simulations.
Re search on path planning with the integration of adaptive a-star alg orithm and improved dynamic window approach,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning
A neural network's predicted guideline and region are used as a reward function and Q-table initializer, cutting Q-learning convergence steps by about 90% in grid path planning simulations.