Deep Ordinal Reinforcement Learning.
Alexander ZapTobias JoppenJohannes FürnkranzPublished in: ECML/PKDD (3) (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- reinforcement learning algorithms
- temporal difference
- case study
- state space
- optimal policy
- data sets
- policy search
- optimal control
- markov decision processes
- real world
- least squares
- evolutionary algorithm
- learning process
- learning algorithm
- control problems
- deep learning
- multi agent reinforcement learning
- real time
- rank correlation
- robotic control
- fitted q iteration