Home
Projects
Publications
People
Join the Lab
Contact
Login
Safety
ROSARL: Reward-Only Safe Reinforcement Learning
An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common …
Geraud Nangue Tasse
,
Tamlin Love
,
Mark Nemecek
,
Steven James
,
Benjamin Rosman
PDF
Cite
Enhancing Agent Safety through Autonomous Environment Adaptation
Exploration and self-directed learning are valuable components of early childhood development. This often comes at an unacceptable …
Benjamin Rosman
,
Bradley Hayes
,
Brian Scassellati
PDF
Cite
Cite
×