Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games.
Yunqiu XuMeng FangLing ChenYali DuJoey Tianyi ZhouChengqi ZhangPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- learning agents
- action sets
- function approximation
- hierarchical model
- markov decision processes
- temporal difference learning
- game theory
- game play
- machine learning
- autonomous mental development
- hierarchical reinforcement learning
- reinforcement learning algorithms
- game playing
- coarse to fine
- learning algorithm
- multimedia
- state space
- video games
- neural network
- game design
- game theoretic
- textual features
- multi agent
- function approximators
- cooperative games
- reinforcement learning agents
- policy search
- search algorithm
- imperfect information
- supervised learning
- unsupervised learning
- computer games
- serious games
- nash equilibrium
- incomplete information