Multigoal Reinforcement Learning via Exploring Entropy-Regularized Successor Matching.
Xiaoyun FengYun ZhouPublished in: IEEE Trans. Games (2023)
Keyphrases
- reinforcement learning
- function approximation
- pattern matching
- matching process
- matching algorithm
- graph matching
- information theory
- reinforcement learning algorithms
- temporal difference
- model free
- information entropy
- shape matching
- multi agent
- machine learning
- ontology matching
- regularized least squares
- risk minimization
- fuzzy entropy
- robotic control
- string matching
- optimal control
- optimal policy
- supervised learning
- least squares
- state space
- web services