A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspectiveby Yunpeng Qing, Shunyu liu, Jingyuan…
An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problemby Runze Guo,…
Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learningby Junseok Park, Yoonsung Kim,…
Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Expertsby Onur Celik, Aleksandar Taranovic,…
Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machinesby Xuejing Zheng, Chao YuFirst submitted to…
In-context Exploration-Exploitation for Reinforcement Learningby Zhenwen Dai, Federico Tomasi, Sina GhiassianFirst submitted to arxiv on:…
Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecificationby Joar Skalse, Alessandro AbateFirst submitted to…
RL-MSA: a Reinforcement Learning-based Multi-line bus Scheduling Approachby Yingzhuo LiuFirst submitted to arxiv on: 11…
Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation…
Scalable Online Exploration via Coverabilityby Philip Amortila, Dylan J. Foster, Akshay KrishnamurthyFirst submitted to arxiv…