Get the latest tech news
Imperial College London, DeepMind introduce embodied agents that learn with less data
Diffusion Augmented Agent proposed by the Imperial College and DeepMind team, is designed to enable agents to learn tasks more efficiently.
“We hypothesize that embodied agents can achieve greater data efficiency by leveraging past experience to explore effectively and transfer knowledge across tasks,” the researchers write. DAAG combines the strengths of LLMs, VLMs, and diffusion models to create agents that can reason about tasks, analyze their environment, and repurpose their past experiences to learn new objectives more efficiently. When the agent receives a new task, the LLM interprets instructions, breaks them into smaller subgoals, and coordinates with the VLM and diffusion model to obtain reference frames for achieving its goals.
Or read this on Venture Beat
