A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning.
Reza Refaei AfsharYingqian ZhangMurat FiratUzay KaymakPublished in: CoRR (2020)
Keyphrases
- knapsack problem
- reinforcement learning
- implicit enumeration
- randomly generated test instances
- dynamic programming
- state space
- combinatorial optimization problems
- optimal solution
- exact algorithms
- optimization problems
- np hard
- np hard problems
- function approximation
- greedy algorithm
- linear programming relaxation
- optimal policy
- bicriteria
- markov decision problems
- maximum profit
- machine learning