Keyphrases
- hierarchical representation
- policy iteration algorithm
- reinforcement learning
- finite state
- markov decision processes
- object centered
- policy iteration
- function approximation
- multiresolution
- coarse to fine
- actor critic
- state space
- model free
- optimal policy
- dynamic programming
- reinforcement learning algorithms
- temporal difference
- partially observable
- supervised learning
- multi agent
- optimal control
- machine learning
- markov chain
- learning algorithm
- partially observable markov decision processes
- object detection
- temporal difference learning
- markov decision problems
- transfer learning
- function approximators
- rl algorithms
- approximate dynamic programming
- image registration
- support vector machine