Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning.
Yuji KanagawaTomoyuki KanekoPublished in: CoG (2019)
Keyphrases
- reinforcement learning
- machine learning
- dynamic programming
- function approximation
- state space
- multi agent
- direct policy search
- learning algorithm
- case study
- optimal policy
- markov decision processes
- optimal control
- model free
- databases
- website
- least squares
- supervised learning
- reinforcement learning algorithms
- control problems
- stochastic approximation
- multi agent reinforcement learning