Playing T-Rex Rush with Deep Reinforcement Learning.
Shuaibing WangJingzheng RenPublished in: CNIOT (2020)
Keyphrases
- reinforcement learning
- function approximation
- model free
- reinforcement learning algorithms
- learning algorithm
- computer games
- game playing
- temporal difference
- state space
- direct policy search
- transfer learning
- markov decision processes
- policy search
- multi agent
- temporal difference learning
- real time
- supervised learning
- card game
- multi agent reinforcement learning
- stochastic approximation
- action space
- deep learning
- data sets
- data mining
- action selection
- machine learning
- information systems
- dynamic programming
- learning problems
- decision problems