- Subtitle:
- Extended abstract
- Abstract:
-
During training, model-free reinforcement learning (RL) systems can explore actions that lead to harmful or costly consequences. Having a human “in the loop” and ready to intervene at all times can prevent these mistakes, but is prohibitively expensive for current algorithms. We explore how human oversight can be combined with a supervised learning system to prevent catastrophic events during training. We demonstrate this scheme on Atari games, with a Deep RL agent being overseen by a human f...
Expand abstract - Publication status:
- Published
- Peer review status:
- Peer reviewed
- Version:
- Publisher's Version
- Publisher:
- ACM Digital Library Publisher's website
- Publication date:
- 2018-07-15
- Acceptance date:
- 2018-04-15
- ISSN:
-
2523-5699
- Pubs id:
-
pubs:966914
- URN:
-
uri:ba0fc61e-1a94-4738-929b-cdfd92fdf49e
- UUID:
-
uuid:ba0fc61e-1a94-4738-929b-cdfd92fdf49e
- Local pid:
- pubs:966914
- Copyright holder:
- International Foundation for Autonomous Agents and Multiagent Systems
- Copyright date:
- 2018
- Notes:
-
© 2018 International Foundation for Autonomous Agents and
Multiagent Systems. The published version is in the form of an extended abstract; the full text of the article has also made available by the author
Conference item
Trial without error: Towards safe reinforcement learning via human intervention
Actions
Authors
Bibliographic Details
Terms of use
Metrics
Altmetrics
Dimensions
If you are the owner of this record, you can report an update to it here: Report update to this record