4 papers
When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation
Matin Aghaei, Lingfeng Zhang, Mohammad Ali Alomrani +2
Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language versus geometry. We revisit this quest…
Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
Lingfeng Zhang, Yuecheng Liu, Zhanguang Zhang +16
Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense…
Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
Max Qiushi Lin, Jincheng Mei, Matin Aghaei +6
Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typica…
Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs
Michael Lu, Matin Aghaei, Anant Raj +1
We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has u…