Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- reinforcement learning algorithms
- state space
- machine learning
- partially observable
- model free
- optimal policy
- learning algorithm
- reward shaping
- supervised learning
- learning process
- reward function
- reinforcement learning methods
- total reward
- learning tasks
- learning classifier systems
- case study
- data sets
- complex domains
- real robot
- policy iteration
- temporal difference learning
- transfer learning