Reinforcement learning with verifiable rewards (RLVR) is widely used to improve reasoning in language models, yet growing evidence suggests that it mostly sharpens what the base model can already do. This raises a practical question: when RL fails, what is the base model missing? We look inside the RL policy's own roll...
The Intelligent Robot Simulator is developed, a lightweight declarative simulator implemented as a Python library to support navigation learning and benchmarking through rapid construction of reusable and diverse scenarios and efficient execution on accessible platforms.
Rui-Hua Han, Shuai Wang, Cheng-Yang Li et al.· 6 citations
Shape-Aware Reinforcement Learned Model Predictive Control is proposed, a method for safe, efficient, and adaptive navigation in crowds with heterogeneous shapes without geometry simplification that preserves the safety structure and generalizability of MPC while integrating the adaptability and intelligence of RL.
SKILLFORGE is introduced, a framework that decomposes formal code synthesis into a library of atomic, reusable skills, each targeting a specific subtask such as specification inference, body synthesis, invariant generation, error diagnosis, or targeted repair, and defined by a prompt template, tool binding, and decidab...
Yan-Ming Liu, Xinyue Peng, Jiannan Cao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
