Efficient Exploration in Edge-Friendly Hyperdimensional Reinforcement Learning.
Yang NiWilliam Youngwoo ChungSamuel ChoZhuowen ZouMohsen ImaniPublished in: ACM Great Lakes Symposium on VLSI (2024)
Keyphrases
- reinforcement learning
- optimal policy
- function approximation
- dynamic programming
- state space
- edge information
- temporal difference learning
- temporal difference
- markov decision processes
- robotic control
- multi agent
- learning process
- edge detection
- genetic algorithm
- weighted graph
- edge detector
- learning algorithm
- scale space
- supervised learning
- undirected graph
- model free
- multiscale
- reinforcement learning algorithms
- action space
- image edges
- multi agent reinforcement learning
- policy search
- machine learning
- friendly interface