6 papers
ANO: Robust Policy Optimization via Bounded, Redescending Gain Fields
Yiheng Zhang, Yiming Wang, Kaiyan Zhao +3
Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment, yet its hard-clipping mechanism and unconstrained alternatives (e.g., SPO) sit at two extreme…
Anon: Extrapolating Adaptivity Beyond SGD and Adam
Yiheng Zhang, Kaiyan Zhao, Shaowu Wu +5
Adaptive optimizers such as Adam and non-adaptive methods like SGD exhibit distinct generalization capabilities across different architectures. Prior tunable optimizers attempt to…
EDT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation
Kaiyan Zhao, Borong Zhang, Yiming Wang +4
In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon tasks. However, DT's perfor…
CT: Captioning-Structure and LLM-Aligned Common-Sense Reward Learning for Traffic--Vehicle Coordination
Yuyang Chen, Kaiyan Zhao, Yiming Wang +3
State-of-the-art (SOTA) urban traffic control increasingly employs Multi-Agent Reinforcement Learning (MARL) to coordinate Traffic Light Controllers (TLCs) and Connected Autonomous…
Efficient Diversity-based Experience Replay for Deep Reinforcement Learning
Kaiyan Zhao, Yiming Wang, Yuyang Chen +3
Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based…
Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
Yuyang Chen, Kaiyan Zhao, Yiming Wang +3
Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation…