Neural Temporal-Difference Learning Converges to Global Optima.
Qi CaiZhuoran YangJason D. LeeZhaoran WangPublished in: NeurIPS (2019)
Keyphrases
- temporal difference learning
- global optima
- global optimization
- fixed point
- function approximation
- optimization problems
- optimization algorithm
- global optimum
- reinforcement learning
- evaluation function
- game playing
- temporal difference
- global search
- neural network
- reinforcement learning algorithms
- premature convergence
- optimal solution
- function optimization
- monte carlo
- evolutionary algorithm
- estimation of distribution algorithms
- machine learning
- markov decision process
- particle swarm
- particle swarm optimization
- genetic programming