Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning.
Yuji KanagawaTomoyuki KanekoPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- machine learning
- reinforcement learning algorithms
- case study
- multi agent
- control problems
- partially observable
- model free
- dynamic programming
- learning process
- direct policy search
- temporal difference learning
- optimal control
- learning problems
- least squares
- real time
- support vector
- multiscale
- decision making
- information systems
- artificial intelligence
- learning algorithm
- data mining