@inproceedings{PhanSommerAltmannetal.2022, author = {Phan, Thomy and Sommer, Felix and Altmann, Philipp and Ritz, Fabian and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Cooperation from Mutual Acknowledgment Exchange}, booktitle = {AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-9213-6}, doi = {https://dl.acm.org/doi/10.5555/3535850.3535967}, pages = {1047 -- 1055}, year = {2022}, language = {en} } @article{PhanSommerRitzetal.2024, author = {Phan, Thomy and Sommer, Felix and Ritz, Fabian and Altmann, Philipp and N{\"u}ßlein, Jonas and K{\"o}lle, Michael and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning}, volume = {38}, pages = {34}, journal = {Autonomous Agents and Multi-Agent Systems}, number = {2}, publisher = {Springer}, address = {Dordrecht}, issn = {1573-7454}, doi = {https://doi.org/10.1007/s10458-024-09666-5}, year = {2024}, abstract = {Peer incentivization (PI) is a recent approach where all agents learn to reward or penalize each other in a distributed fashion, which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly incorporated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information, which limits scalability and applicability to real-world scenarios where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to exchange acknowledgment tokens as incentives to shape individual rewards mutually. All agents condition their token transmissions on the locally estimated quality of their own situations based on environmental rewards and received tokens. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can deviate from the protocol and communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.}, language = {en} } @unpublished{PhanSommerRitzetal.2022, author = {Phan, Thomy and Sommer, Felix and Ritz, Fabian and Altmann, Philipp and N{\"u}ßlein, Jonas and K{\"o}lle, Michael and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Cooperation from Mutual Acknowledgment Exchange in Multi-Agent Reinforcement Learning}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-2315844/v1}, year = {2022}, abstract = {Peer incentivization (PI) is a recent approach, where all agents learn to reward or to penalize each other in a distributed fashion which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly integrated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information which limits scalability and applicability to real-world scenarios, where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to mutually exchange acknowledgment tokens to shape individual rewards. Each agent evaluates the monotonic improvement of its individual situation in order to accept or reject acknowledgment requests from other agents. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can defect from the protocol and where communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.}, language = {en} }