Great work using offline agentic exploration to develop robot skills!
Children learn from play. Can robots do the same?
We propose 𝐏𝐥𝐚𝐲𝐟𝐮𝐥 𝐀𝐠𝐞𝐧𝐭𝐢𝐜 𝐑𝐨𝐛𝐨𝐭 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠, a paradigm that gives embodied coding agents a play stage before downstream tasks arrive, and instantiate it with 𝐑𝐀𝐓𝐬 (Robotics Agent Teams), where robots discover reusable skills through curious play.
Co-led with @jiaxin_ge_
Users are excited about the RATs paradigm for embodied agents because it lets robots build reusable skill libraries through curiosity-driven play before any human task is specified.
No Digg Deeper questions have been answered for this story yet.
@letian_fu @nvidia @_wenlixiao @DrJimFan What can agents learn before a human specifies the task? THIS is the question. Robots building skill libraries through play could crack the programming bottleneck wide open.
While ENPIRE w/ @nvidia @_wenlixiao @DrJimFan enables coding agents to explore algorithms and improve policies for a given real-world task, RATs asks: what can agents learn before a human specifies the task?
Through curiosity-driven play, agents propose tasks, hill-climb toward solutions, and accumulate reusable, transferable skills. When a human later requests a new task, the agents retrieve and compose these skills to solve it.
RATs explores an analogue of pre-training for embodied coding agents: broad skill acquisition through play, which accelerates task-specific problem solving with the skills acquired.
Looking forward to the agentic future of robotics!
See the detailed tweet from @junyi42!
Children learn from play. Can robots do the same?
We propose 𝐏𝐥𝐚𝐲𝐟𝐮𝐥 𝐀𝐠𝐞𝐧𝐭𝐢𝐜 𝐑𝐨𝐛𝐨𝐭 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠, a paradigm that gives embodied coding agents a play stage before downstream tasks arrive, and instantiate it with 𝐑𝐀𝐓𝐬 (Robotics Agent Teams), where robots discover reusable skills through curious play.
Co-led with @jiaxin_ge_
@letian_fu @nvidia @_wenlixiao @DrJimFan @roeiherzig