Reinforcement Learning in Non-Stationary Discrete-Time Linear-Quadratic Mean-Field Games

Keyphrases

• Actor-critic Algorithm 66%
• Backward in Time 33%
• Causal Reinforcement Learning 33%
• Convergence Guarantee 33%
• Discrete-time 100%
• Error Bound 33%
• Finite Population Games 33%
• Finite Sample 33%
• Infinite Horizon 33%
• Large Population 33%
• Linear Dynamics 33%
• Linear Quadratic 100%
• Linear Quadratic Gaussian 33%
• Linear Quadratic Tracking 33%
• Markov Chain 66%
• Mean Field 33%
• Mean Field Equilibrium 33%
• Mean Field Games 100%
• Multi-agent Reinforcement Learning 66%
• Nash Equilibrium 33%
• Non-stationarity 33%
• Quadratic Mean 100%
• Reinforcement Learning 100%
• Reinforcement Learning Algorithm 66%
• Stationary Distribution 33%

Mathematics

• Data Source 50%
• Discrete Time 100%
• Error Bound 50%
• Finite Population 50%
• Gaussian Distribution 50%
• Markov Chain 100%
• Nash Equilibrium 50%
• Real Data 50%
• Stationarity 50%