Title | ||
---|---|---|
Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach. |
Abstract | ||
---|---|---|
The Iterated Prisoneru0027s Dilemma has guided research on social dilemmas for decades. However, it distinguishes between only two atomic actions: cooperate and defect. In real-world prisoneru0027s dilemmas, these choices are temporally extended and different strategies may correspond to sequences of actions, reflecting grades of cooperation. We introduce a Sequential Prisoneru0027s Dilemma (SPD) game to better capture the aforementioned characteristics. In this work, we propose a deep multiagent reinforcement learning approach that investigates the evolution of mutual cooperation in SPD games. Our approach consists of two phases. The first phase is offline: it synthesizes policies with different cooperation degrees and then trains a cooperation degree detection network. The second phase is online: an agent adaptively selects its policy based on the detected degree of opponent cooperation. The effectiveness of our approach is demonstrated in two representative SPD 2D games: the Apple-Pear game and the Fruit Gathering game. Experimental results show that our strategy can avoid being exploited by exploitative opponents and achieve cooperation with cooperative opponents. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Artificial Intelligence | Computer science,Artificial intelligence,Dilemma,Adversary,Atomic actions,Iterated function,Social dilemma,Machine learning,Reinforcement learning |
DocType | Volume | Citations |
Journal | abs/1803.00162 | 0 |
PageRank | References | Authors |
0.34 | 15 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weixun Wang | 1 | 1 | 5.75 |
Jianye Hao | 2 | 189 | 55.78 |
Yixi Wang | 3 | 0 | 1.01 |
Matthew E. Taylor | 4 | 1352 | 94.88 |