Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Duque, Juan Agustin"'
Autor:
Duque, Juan Agustin, Aghajohari, Milad, Cooijmans, Tim, Ciuca, Razvan, Zhang, Tianyu, Gidel, Gauthier, Courville, Aaron
Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts, particular
Externí odkaz:
http://arxiv.org/abs/2406.14662
In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiquitous relevance of such settings, decentralized machine learning algor
Externí odkaz:
http://arxiv.org/abs/2405.01035
We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooperation. LOLA and POLA agents learn reciprocity-based cooperative polici
Externí odkaz:
http://arxiv.org/abs/2404.06519