Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectives.
Alper Kamil BozkurtYu WangMichael M. ZavlanosMiroslav PajicPublished in: CoRR (2020)
Keyphrases
- stochastic games
- linear temporal logic
- model free reinforcement learning
- temporal logic
- reinforcement learning
- nash equilibria
- model checking
- markov decision processes
- average reward
- nash equilibrium
- reinforcement learning algorithms
- multi agent
- imperfect information
- learning automata
- single agent
- robust optimization
- learning agent
- infinite horizon
- incomplete information
- optimal policy