Efficiently Training Deep-Learning Parametric Policies using Lagrangian Dualityby Andrew Rosemberg, Alexandre Street, Davi M. Valladão,…
Privileged Sensing Scaffolds Reinforcement Learningby Edward S. Hu, James Springer, Oleh Rybkin, Dinesh JayaramanFirst submitted…
Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergenceby Minheng Xiao, Xian Yu,…
AGILE: A Novel Reinforcement Learning Framework of LLM Agentsby Peiyuan Feng, Yichen He, Guanhua Huang,…
Discretization of continuous input spaces in the hippocampal autoencoderby Adrian F. Amil, Ismael T. Freire,…
Closed-form Solutions: A New Perspective on Solving Differential Equationsby Shu Wei, Yanjie Li, Lina Yu,…
Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiencesby Takuya Hiraoka,…
DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Modelsby Jingyi Chen, Ju-Seung Byun,…
State-Constrained Offline Reinforcement Learningby Charles A. Hepburn, Yue Jin, Giovanni MontanaFirst submitted to arxiv on:…
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationby Yang Zhang, Shixin Yang, Chenjia Bai, Fei…