RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark.
Federico BertoChuanbo HuaJunyoung ParkMinsu KimHyeonah KimJiwoo SonHaeyeon KimJoungho KimJinkyoo ParkPublished in: CoRR (2023)
Keyphrases
- combinatorial optimization
- reinforcement learning
- combinatorial optimization problems
- metaheuristic
- traveling salesman problem
- simulated annealing
- function approximation
- branch and bound algorithm
- state space
- real world
- branch and bound
- optimization problems
- reinforcement learning algorithms
- combinatorial problems
- model free
- mathematical programming
- markov decision processes
- optimal policy
- temporal difference
- dynamic programming
- rl algorithms
- policy iteration
- learning algorithm
- action selection
- single machine scheduling problem
- control policy
- direct policy search
- transfer learning
- multi agent
- machine learning
- exact algorithms
- function approximators
- combinatorial search
- hard combinatorial optimization problems
- partially observable domains
- learning classifier systems
- optimal control
- learning problems
- optimal solution
- genetic algorithm