Unsupervised pre-training has recently become the bedrock for computer v...
Passive observational data, such as human videos, is abundant and rich i...
Meta-reinforcement learning algorithms provide a data-driven way to acqu...
Offline RL algorithms must account for the fact that the dataset they ar...
Generalization is a central challenge for the deployment of reinforcemen...
We identify an implicit under-parameterization phenomenon in value-based...
Reinforcement learning with function approximation can be unstable and e...
Model-free deep reinforcement learning algorithms are troubled with poor...
Imitation learning algorithms provide a simple and straightforward appro...
Representation learning is a central challenge across a range of machine...
The design of a reward function often poses a major practical challenge ...
Standard model-free deep reinforcement learning (RL) algorithms sample a...