Towards Cooperation In Sequential Prisoner's Dilemmas: A Deep Multiagent Reinforcement Learning Approach
2018 · Weixun Wang, Jianye Hao, Yixi Wang, et al.
Abstract
The Iterated Prisoner's Dilemma has guided research on social dilemmas for decades. However, it distinguishes between only two atomic actions: cooperate and defect. In real-world prisoner's dilemmas, these choices are temporally extended and different strategies may correspond to sequences of actions, reflecting grades of cooperation. We introduce a Sequential Prisoner's 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
Authors
(none)
Tags
Stats
Related papers
- Cooperation Dynamics In Multi-agent Systems: Exploring Game-theoretic Scenarios With Mean-field Equilibria (2023)0.00
- Learning Through Probing: A Decentralized Reinforcement Learning Architecture For Social Dilemmas (2018)0.00
- Dilution, Diffusion And Symbiosis In Spatial Prisoner's Dilemma With Reinforcement Learning (2025)0.00
- Learning Multiagent Coordination In The Absence Of Communication Channels (2018)0.00
- Online Learning In Iterated Prisoner's Dilemma To Mimic Human Behavior (2020)0.00
- Intrinsic Fluctuations Of Reinforcement Learning Promote Cooperation (2022)9.23
- Improved Cooperation By Balancing Exploration And Exploitation In Intertemporal Social Dilemma Tasks (2021)0.00
- Symmetric Equilibrium Of Multi-agent Reinforcement Learning In Repeated Prisoner's Dilemma (2021)8.60