Precision home robots learn with real-to-sim-to-real | MIT News
4 Mins read
At the top of many automation wish lists is a particularly time-consuming task: chores. The moonshot of many roboticists is cooking up…
A better way to control shape-shifting soft robots | MIT News
4 Mins read
Imagine a slime-like robot that can seamlessly change its shape to squeeze through narrow spaces, which could be deployed inside the human…
New method uses crowdsourced feedback to help train robots | MIT News
5 Mins read
To teach an AI agent a new task, like how to open a kitchen cabinet, researchers often use reinforcement learning — a…
A four-legged robotic system for playing soccer on various terrains | MIT News
5 Mins read
If you’ve ever played soccer with a robot, it’s a familiar feeling. Sun glistens down on your face as the smell of…
Why do Policy Gradient Methods work so well in Cooperative MARL? Evidence from Policy Representation
5 Mins read
In cooperative multi-agent reinforcement learning (MARL), due to its on-policy nature, policy gradient (PG) methods are typically believed to be less sample…
Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation – The Berkeley Artificial Intelligence Research Blog
4 Mins read
Reinforcement learning provides a conceptual framework for autonomous agents to learn from experience, analogously to how one might train a pet with…