Incorporating Actor-Critic in Monte Carlo tree search for symbolic regression.
Qiang LuFan TaoShuo ZhouZhiguang WangPublished in: Neural Comput. Appl. (2021)
Keyphrases
- monte carlo tree search
- temporal difference
- monte carlo
- genetic programming
- evaluation function
- function approximation
- reinforcement learning
- optimal control
- game tree
- temporal difference learning
- markov chain
- action selection
- policy iteration
- fixed point
- step size
- model free
- computational intelligence
- reinforcement learning algorithms
- genetic algorithm