Policy Gradient Play with Networked Agents in Markov Potential Games.
Sarper AydinCeyhun EksinPublished in: L4DC (2023)
Keyphrases
- multiagent learning
- policy gradient
- multi agent
- single agent
- multi agent systems
- game players
- game playing
- game theoretic
- nash equilibria
- multiple agents
- stochastic games
- cooperative
- autonomous agents
- human players
- game description language
- computer games
- reinforcement learning
- game theory
- imperfect information
- dynamic environments
- video games
- gradient method
- state action
- resource allocation