"Trial without Error: Towards Safe Reinforcement Learning via Human ..."

William Saunders et al. (2018)

> Home

Details and statistics

DOI: —

access: closed

type: Conference or Workshop Paper

metadata version: 2018-07-16

- view
  - electronic edition @ acm.org
- export record
  dblp key:
  - conf/atal/SaundersSSE18
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/atal/SaundersSSE18
William Saunders, Girish Sastry, Andreas Stuhlmüller, Owain Evans:
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention. AAMAS 2018: 2067-2069

a service of

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.