Joy, distress, hope, and fear in reinforcement learning.
Elmer JacobsJoost BroekensCatholijn M. JonkerPublished in: AAMAS (2014)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- temporal difference learning
- control problems
- reinforcement learning algorithms
- direct policy search
- machine learning
- multi agent reinforcement learning
- model free
- markov decision processes
- optimal policy
- multi agent
- state space
- optimal control
- markov decision process
- robotic control
- learning classifier systems
- dynamic programming
- learning process
- learning capabilities
- knowledge base
- continuous state
- information systems
- active exploration
- artificial intelligence