Feature Reinforcement Learning: Part II. Structured MDPs.
Marcus HutterPublished in: J. Artif. Gen. Intell. (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- markov decision process
- optimal policy
- function approximation
- state and action spaces
- reinforcement learning algorithms
- real world
- action space
- model based reinforcement learning
- model free
- policy search
- policy iteration
- approximate dynamic programming
- image features
- temporal difference
- feature vectors
- control problems
- continuous state
- action sets
- continuous state and action spaces
- continuous state spaces
- policy evaluation
- temporal difference learning
- reward function
- feature set
- supervised learning
- feature selection
- machine learning