Improvements and Generalizations of Stochastic Knapsack and Multi-Armed Bandit Approximation Algorithms: Extended Abstract.
Will MaPublished in: SODA (2014)
Keyphrases
- extended abstract
- approximation algorithms
- multi armed bandit
- np hard
- multi armed bandits
- knapsack problem
- special case
- reinforcement learning
- approximation schemes
- vertex cover
- worst case
- dynamic programming
- regret bounds
- upper bound
- optimal solution
- set cover
- approximation ratio
- randomized algorithms
- primal dual
- greedy heuristic
- disjoint paths
- learning algorithm
- packing problem
- constant factor
- computational complexity
- closed form
- resource allocation
- lower bound