Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics.
Aamal Abbas HussainFrancesco BelardinelliGeorgios PiliourasPublished in: IJCAI (2023)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- initial conditions
- agent based simulations
- multi agent simulation
- single agent
- stochastic approximation
- intelligent agents
- multi agent systems
- dynamical systems
- cooperative agents
- heterogeneous agents
- dynamic model
- stochastic shortest path
- multiple agents
- exact solution
- coalition formation
- convergence speed
- autonomous agents
- iterative algorithms
- multiagent learning
- convergence rate
- software agents
- multiagent systems
- agent based models
- function approximation
- multiagent reinforcement learning
- oriented programming
- dynamic programming