University of Cambridge > Talks.cam > Engineering Safe AI > Reinforcement learning with a corrupted reward function

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Reinforcement learning with a corrupted reward function

Download to your calendar using vCal

If you have a question about this talk, please contact Adrià Garriga Alonso .

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. Two ways around the problem are investigated.

This talk is part of the Engineering Safe AI series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Live Zoom webinar, followed by Q&A session Cambridge IR and History Seminar Series Seminar Room, Centre for Animal Welfare & Anthrozoology, Department of Veterinary Medicine, Madingley Road, Cambridge

Other talks

The role of radiation in cancer care: a spotlight on cancers of the oesophagus, head and neck An Amphibious Urbanism | | Cut 4: The Desert Arrives Slowly Disentangling preventative & ejective AGN feedback on a population basis with simulations, observations & machine learning Title TBC Online Causal Inference Seminar Title to be confirmed
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity