🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

One more 🤯! We are delighted to announce that @googleresearch will support our workshop Gamification and Multiagent Solutions Workshop ICLR 2026 2022 🥳 We are looking forward to seeing you at the workshop 🔥

The list of accepted papers is on our website: gamificationmas.com/accepted-papers Check this out!

📅 Finally! Meet us tomorrow at our Gamification and Multiagent Solutions Workshop ICLR 2026! More details on our website: gamificationmas.com We are looking forward to meeting you there! Full program 👇👇👇

Happening now!

Thank to everyone that came and participated to our Gamification and Multiagent Solutions workshop ICLR 2026 🤗 As organizers of our first workshop, it was a lot of work but we are looking forward to doing it again in the future. Now it's time to announce the awards 🏅

🏆 BEST PAPER AWARD 🏆 V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL Congrats to Chi Jin, Qinghua Liu, Yuanhao Wang and Tiancheng Yu!

🏆 BEST POSTER AWARD 🏆 A Regret Minimization Approach to Multi-Agent Control Congrats to Udaya Ghai, Udari Madhushani Sehwag, Naomi Leonard and Elad Hazan!

🏆 BEST COOPERATIVE AI PAPER AWARD 🏆 Learning to Share in Multi-Agent Reinforcement Learning Congrats to Yuxuan Yi, Ge Li, Yaowei Wang and Zongqing Lu! Many thanks to our sponsor Cooperative AI Foundation.

🏆 BEST COOPERATIVE AI POSTER AWARD 🏆 Introducing Coordination in Concurrent Reinforcement Learning Congrats to Adrien Alitaiga, Aaron Courville and Marc G. Bellemare! Many thanks to our sponsor Cooperative AI Foundation.

We leverage the most basic democratic principle of "one person one vote" to learn a value-aligned mediator for complex multiagent interactions (e.g. social nets, traffic routing). Our intepretable mediator is preferred by humans over strong alternatives. arxiv.org/abs/2202.10122

DeepNash is an agent trained with model-free multiagent reinforcement learning that learns to play the game of Stratego at expert level. Learn more: dpmd.ai/DM-DeepNash 1/

In a new Nature Human Behaviour paper, our team trained an AI system to distribute resources according to human preferences, fostering cooperation and fairness. Read more at dpmd.ai/dm-mechanism-d… and dpmd.ai/nhb-mechanism-… 1/

Work by Raphael Koster, Jan Balaguer, Andrea Tacchetti, Ari Weinstein, Tina Zhu, Oliver Hauser (University of Exeter Business School), Duncan Williams, Lucy Campbell-Gillingham, Phoebe Thacker, Matthew Botvinick, and summerfieldlab @summerfieldlab.bsky.social. 2/2

#AI can learn to produce a reward policy for an incentivized multiplayer game which is preferred by the players themselves. summerfieldlab @summerfieldlab.bsky.social buff.ly/3AphgaU

Recordings from our workshop are now publicly accessible at: iclr.cc/virtual/2022/w… Thanks again to our amazing speakers and participants!

Today in Nature Communications, we explore how AI agents can better communicate and cooperate in Diplomacy - a 7-player board game of coordination and alliance formation. 🤝 Find out more: dpmd.ai/diplomacy-natu…

.Yoram Bachrach János Kramár Ian Gemp Andrea Tacchetti Kevin McKee Mateusz Malinowski Thore Graepel et al. report how to make intelligent agents communicate and negotiate honestly in the board game of Diplomacy @DeepMind #AI #GettingApplied nature.com/articles/s4146…

Altruism and selfishness are highly transmissible. Here, we learn to structure networks of human participants playing a group cooperation game. Under our social planner, groups had an average cooperation rate of 77.7%, compared to 42.8% in static networks psyarxiv.com/cr58a/

Exciting News from Chatbot Arena! Google DeepMind's new Gemini 1.5 Pro (Experimental 0801) has been tested in Arena for the past week, gathering over 12K community votes. For the first time, Google Gemini has claimed the #1 spot, surpassing GPT-4o/Claude-3.5 with an impressive