Towards a Deep Reinforcement Learning Approach for Tower Line Wars.
Per-Arne AndersenMorten GoodwinOle-Christoffer GranmoPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- learning algorithm
- temporal difference
- machine learning
- data sets
- optimal policy
- action space
- robot control
- learning capabilities
- model free
- dynamical systems
- line segments
- supervised learning
- dynamic programming
- active learning
- learning process
- search algorithm
- computer vision