Ethical Decision Making
TLDR: Enable autonomous systems to comply with ethical theories.
Adversarial Robustness
TLDR: Safeguard LLMs against adversarial attacks.
State Abstractions
TLDR: Solve MDPs using partial state abstractions.
Exception Recovery
TLDR: Allow autonomous systems to recover from exceptions.
Optimal Stopping
TLDR: Optimize the stopping point of anytime planners.
Agent-Aware State Estimation
TLDR: Enable autonomous systems to discover their state by observing the behavior of other agents.
Competence Awareness
TLDR: Allow autonomous systems to learn/improve their competence via human feedback.
Safe Decision Making
TLDR: Enable autonomous systems to be more safe.
Optimal Hyperparameter Tuning
TLDR: Optimize the hyperparameters of anytime planners.
Agent Architectures
TLDR: Formally compose the architecture of agents.
Active Teacher Selection
TLDR: Actively select teachers during RLHF.