Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients.
Daniel HennesDustin MorrillShayegan OmidshafieiRémi MunosJulien PérolatMarc LanctotAudrunas GruslysJean-Baptiste LespiauPaavo ParmasEdgar A. Duéñez-GuzmánKarl TuylsPublished in: AAMAS (2020)
Keyphrases
- multiagent learning
- replicator dynamics
- multi agent learning
- evolutionary game theory
- multi agent
- game theory
- multi agent reinforcement learning
- artificial intelligence
- neural network
- resource allocation
- complex domains
- policy gradient
- multiagent systems
- learning agents
- optimal policy
- multi agent systems
- nash equilibria
- graph matching
- game theoretic