Group
Group
Development and evaluation of agentic systems. Interactions of small and large language models.
Benjamin Unger (Visiting Researcher, ETH)
Mean-field multi-agent RL.Benjamin Unger (Visiting Researcher, ETH)
Mean-field multi-agent RL.Ankur Samanta (Columbia & Meta)
Post-training on multi-agent debate.Runzhe Wu (Cornell Tech)
Post-training with multiple reward functions.Ben Kretzu (Technion)
Aligned multi-objective optimization.Wenhao Zhan (Princeton)
Offline multi-agent reinforcement learning with small interaction-rank.Jeongyeol Kwon (Meta)
Reinforcement learning in latent Markov Decision Processes.Manan Tomar (Microsoft)
Mirror-Descent Policy Optimization; Multi-step greedy deep reinforcement learning.