TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment
The Reinforcement Learning (RL) paradigm has achieved remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, when applied to long-horizon tasks, it faces severe challenges: i) Due to the high task complexity, the model struggles to sample enough successful trajectories, res...
Yi Wen, Hao Chen, Wan-Yu Wang et al.
· 0 citations