Two papers about fine-tuning LLMs for decision-making tasks, AdaRefiner and LLaMA-Rider, were accepted at NAACL’24.
Three papers respectively on LMMs, policy pre-training and offline RL were accepted at ICLR’24. Additionally, we have one paper accepted at TMLR, two at AAAI’24, and two at AAMAS’24. Congratulations to all.
Our two papers about learning from observation and multi-agent reinforcement learning were accepted at NeurIPS’23. Congratulations to Bohan and Jiangxing.
Our two papers about language learning and language grounding via reinforcement learning were respectively accepted at ACL’23 and ICML’23.
Our paper, MA2ML, was accepted at CVPR’23. MA2ML is a MARL algorithm for full-pipeline automated machine learning.
Our three papers, MACPF, OTC, and AdaMa were respectively accepted at ICLR’23, AAAI’23, and AAMAS’23.
Our six papers about reinforcement learning were accepted at NIPS’22.
Our three papers about multi-agent RL and offline RL were accepted at ICML’22.
Our paper “Learning to Share in Multi-Agent Reinforcement Learning” won the Best Cooperative AI Paper Award at ICLR’22 Workshop on Gamification and Multiagent Solutions.
Our two papers, EOI and FOP, were accepted at ICML’21.