Beyond Strict Competition: Approximate Convergence of Multi Agent Q-Learning Dynamics.
Aamal Abbas HussainFrancesco BelardinelliGeorgios PiliourasPublished in: CoRR (2023)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- initial conditions
- agent based simulations
- multi agent simulation
- stochastic approximation
- intelligent agents
- multiagent systems
- multi agent systems
- single agent
- multiagent learning
- learning algorithm
- agent based models
- software agents
- autonomous agents
- multiple agents
- convergence speed
- dynamic model
- learning agents
- exact solution
- agent oriented
- optimal policy
- iterative algorithms
- state space
- multi agent learning
- tracking error
- multi agent reinforcement learning
- team formation
- dynamical systems