We investigate the use of transformer sequence models as dynamics models...
Sequential decision-making agents struggle with long horizon tasks, sinc...
Inspired by progress in large-scale language modeling, we apply a simila...
Imitation learning enables agents to reuse and adapt the hard-won expert...
Deep reinforcement learning has been shown to solve challenging tasks wh...
When learning behavior, training data is often generated by the learner
...
Current end-to-end Reinforcement Learning (RL) approaches are severely
l...
Model-free reinforcement learning has recently been shown to be effectiv...
Recently, model-free reinforcement learning algorithms have been shown t...
A robot that can carry out a natural-language instruction has been a dre...