On the Convergence of Reinforcement Learning.
Suman ChakravortyRan WangMohamed Naveed Gul MohamedPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- stochastic approximation
- function approximation
- reinforcement learning algorithms
- robot control
- state space
- model free
- convergence rate
- learning algorithm
- temporal difference
- convergence speed
- temporal difference learning
- iterative algorithms
- policy iteration
- markov decision processes
- supervised learning
- neural network
- robotic control
- reinforcement learning methods
- optimal control
- learning tasks
- decision trees
- decision making
- machine learning