The Role of Network Topology and Opponent Information in Shaping Cooperation in Multi-Agent Reinforcement Learning Systems
Experimental results show that the number of neighbours per node and the average path length are the main factors affecting the emergence of cooperation in scenarios in which each agent learns to play the two-player Iterated Prisoner's Dilemma using deep reinforcement learning.
Seongho Son, Stephen Hailes, Mirco Musolesi
· 0 citations