Reusability and Transferability of Macro Actions for Reinforcement Learning.
Yi-Hsiang ChangKuan-Yu ChangHenry KuoChun-Yi LeePublished in: ACM Trans. Evol. Learn. Optim. (2022)
Keyphrases
- macro actions
- reinforcement learning
- markov decision processes
- state space
- reinforcement learning algorithms
- function approximation
- temporal difference
- model free
- learning algorithm
- linear programming
- machine learning
- dynamic programming
- learning process
- multi agent
- e learning
- markov decision process
- reinforcement learning methods
- optimal policy
- neural network
- policy iteration
- action space
- continuous state