Learning Heuristic Policies - A Reinforcement Learning Problem.
Thomas Philip RunarssonPublished in: LION (2011)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- learning systems
- optimal policy
- hierarchical reinforcement learning
- action selection
- policy gradient methods
- reinforcement learning methods
- learning problems
- optimal solution
- knowledge acquisition
- learning tasks
- dynamic programming
- function approximation
- active learning
- reinforcement learning algorithms
- robot control
- temporal difference learning
- prior knowledge
- policy search
- search algorithm
- reinforcement learning agents