Finite-time complexity of incremental policy gradient methods for solving multi-task reinforcement learning.
Yitao BaiThinh T. DoanPublished in: L4DC (2024)
Keyphrases
- multi task
- reinforcement learning
- policy gradient methods
- multi task learning
- learning problems
- learning tasks
- transfer learning
- natural actor critic
- policy gradient
- multi class
- actor critic
- state space
- function approximators
- machine learning
- function approximation
- feature selection
- markov decision problems
- learning algorithm
- model free
- neural network
- approximate dynamic programming
- labeled data
- learning process
- data mining