Final Iteration Convergence Bound of Q-Learning: Switching System Approach.
Donghwan LeePublished in: IEEE Trans. Autom. Control. (2024)
Keyphrases
- stochastic approximation
- number of iterations required
- iterative algorithms
- stopping criterion
- reinforcement learning
- convergence rate
- cooperative
- stochastic shortest path
- upper bound
- learning algorithm
- multi agent
- state space
- function approximation
- learning rate
- convergence speed
- lower bound
- convergence proof
- monte carlo
- line search
- error bounds
- temporal difference learning
- machine learning
- neural network
- optimal policy
- worst case
- action selection
- reinforcement learning algorithms
- policy iteration
- global convergence
- bucket brigade