Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation Systemby Yang Zhao,…
PWM: Policy Learning with Multi-Task World Modelsby Ignat Georgiev, Varun Giridhar, Nicklas Hansen, Animesh GargFirst…
Optimizing Age of Information in Vehicular Edge Computing with Federated Graph Neural Network Multi-Agent Reinforcement…
Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learningby Yifang Chen, Shuohang Wang, Ziyi…
Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learningby Zakariae El Asri, Olivier Sigaud,…
Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agentsby Fanzeng Xia, Hao Liu, Yisong Yue,…
Text-Aware Diffusion for Policy Learningby Calvin Luo, Mandy He, Zilai Zeng, Chen SunFirst submitted to…
A Deep Reinforcement Learning Approach to Battery Management in Dairy Farming via Proximal Policy Optimizationby…
Weight Clipping for Deep Continual and Reinforcement Learningby Mohamed Elsayed, Qingfeng Lan, Clare Lyle, A.…
Normalization and effective learning rates in reinforcement learningby Clare Lyle, Zeyu Zheng, Khimya Khetarpal, James…