To interact with humans in the world, agents need to understand the dive...
Learning from human feedback has been shown to improve text-to-image mod...
Deep generative models have shown impressive results in text-to-image
sy...
Reinforcement learning algorithms typically struggle in the absence of a...
Training automated agents to complete complex tasks in interactive
envir...
In order for humans to confidently decide where to employ RL agents for
...
Policies trained in simulation often fail when transferred to the real w...
Many challenges in natural language processing require generating text,
...
The task of translating between programming languages differs from the
c...