Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation.
Daniel VialAdvait ParulekarSanjay ShakkottaiR. SrikantPublished in: CoRR (2021)
Keyphrases
- function approximation
- regret bounds
- shortest path problem
- temporal difference learning algorithms
- reinforcement learning
- lower bound
- online learning
- linear regression
- function approximators
- shortest path
- temporal difference
- learning tasks
- model free
- combinatorial optimization problems
- upper bound
- radial basis function
- multiple objectives
- genetic algorithm
- multi objective
- directed graph
- directed acyclic graph
- simulated annealing
- collaborative filtering
- semi supervised
- cost function
- artificial neural networks
- decision trees
- machine learning