Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on robotics is the subjec t of a new report. According to news originating from Shanghai, People's Republi c of China, by NewsRx editors, the research stated, "The inferior sample efficie ncy of reinforcement learning (RL) and the requirement for high-quality demonstr ations in imitation learning (IL) will hinder their application in real-world ro bots." Financial supporters for this research include National Natural Science Foundati on of China; Shanghai Crossdisciplinary Research Fund. Our news correspondents obtained a quote from the research from Shanghai Jiao To ng University: "To address this challenge, a novel self-evolution framework, nam ed task-oriented self-imitation learning (TOSIL), is proposed. To circumvent ext ernal demonstrations, the top-K self-generated trajectories are chosen as expert data from both per-episode exploration and long-term return perspectives. Each transition is assigned a guide reward, which is formulated by these trajectories . The guide rewards update as the agent evolves, encouraging good exploration be haviors. This methodology guarantees that the agent explores in the direction re levant to the task, improving sample efficiency and asymptotic performance. The experimental results on locomotion and manipulation tasks indicate that the prop osed framework outperforms other state-of-the-art RL methods."
NETL
NSTL