RL-CSL: A Combinatorial Optimization Method Using Reinforcement Learning and Contrastive Self-Supervised Learning.
Zhongju YuanGenghui LiZhenkun WangJianyong SunRan ChengPublished in: IEEE Trans. Emerg. Top. Comput. Intell. (2023)
Keyphrases
- reinforcement learning
- optimization method
- learning algorithm
- learning process
- function approximation
- rl algorithms
- temporal difference learning
- autonomous learning
- optimization algorithm
- markov decision processes
- reinforcement learning methods
- learning problems
- state space
- optimization process
- model free
- action selection
- optimal policy
- learning tasks
- optimization methods
- reinforcement learning algorithms
- supervised learning
- temporal difference
- multi agent
- learning capabilities
- partially observable
- learning agent
- action space
- function approximators
- cost function
- metaheuristic
- simulated annealing
- actor critic
- partially observable domains