4 papers
CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution
Jinyuan Feng, Dongmin Li, Yiqun Chen +4
Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural knowledge. Yet existing parad…
Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control
Hao Ma, Zhiqiang Pu, Xiaolin Ai +1
We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (L…
Stochastic Trajectory Prediction under Unstructured Constraints
Hao Ma, Zhiqiang Pu, Shijie Wang +4
Trajectory prediction facilitates effective planning and decision-making, while constrained trajectory prediction integrates regulation into prediction. Recent advances in constrai…
OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning
Jinyuan Feng, Zhiqiang Pu, Tianyi Hu +3
Building mixture-of-experts (MoE) architecture for Low-rank adaptation (LoRA) is emerging as a potential direction in parameter-efficient fine-tuning (PEFT) for its modular design…