Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation.
Arnob GhoshPublished in: CoRR (2022)
Keyphrases
- function approximation
- model free
- reinforcement learning
- policy iteration
- reinforcement learning algorithms
- temporal difference
- average reward
- function approximators
- temporal difference learning
- leader follower
- policy evaluation
- learning tasks
- markov decision processes
- radial basis function
- rl algorithms
- state space
- neural network
- optimal policy
- machine learning
- learning problems
- reinforcement learning methods
- learning algorithm
- optimal control
- finite state
- transfer learning
- support vector machine
- mobile robot
- dynamic programming
- learning process
- artificial neural networks