Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games.
Patrick PhillipsPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- action sets
- action selection
- learning agents
- extensive form games
- action space
- state space
- partially observable domains
- reward shaping
- state action
- reinforcement learning algorithms
- function approximation
- reinforcement learning agents
- machine learning
- video games
- computer games
- multi agent
- transition model
- learning algorithm
- optimal policy
- markov decision processes
- model free
- game theory
- sensory inputs
- fitted q iteration
- serious games
- multiagent learning
- game design
- markov decision process
- partially observable
- temporal difference learning
- temporal difference
- continuous state
- game playing
- optimal control
- stochastic games
- nash equilibria
- cooperative