Offline reinforcement learning (RL) is a promising direction that allows...
A robot deployed in a home over long stretches of time faces a true life...
Despite the advancement of machine learning techniques in recent years,
...
A hallmark of human intelligence is the ability to construct self-contai...
A major goal of artificial intelligence (AI) is to create an agent capab...
We present CompoSuite, an open-source simulated robotic manipulation
ben...
Learning task-oriented dialog policies via reinforcement learning typica...
Methods for learning from demonstration (LfD) have shown success in acqu...
Humans commonly solve complex problems by decomposing them into easier
s...
While deep neural networks (DNNs) have achieved impressive classificatio...
A hallmark of human intelligence is the ability to construct self-contai...
Policy gradient methods have shown success in learning control policies ...