Iterated Deep Reinforcement Learning in Games: History-Aware Training for Improved Stability.
Mason WrightYongzhao WangMichael P. WellmanPublished in: EC (2019)
Keyphrases
- reinforcement learning
- serious games
- learning agents
- deep architectures
- supervised learning
- video games
- nash equilibria
- state space
- computer games
- function approximation
- deep learning
- markov decision processes
- multi agent
- training examples
- reinforcement learning agents
- training set
- training process
- stability analysis
- imperfect information
- data sets
- stochastic games
- multiagent learning
- learning agent
- action selection
- educational games
- nash equilibrium
- incomplete information
- dynamic programming