Safely interruptible agents
Reinforcement learning agents interacting with a complex environment like the real world are unlikely to behave optimally all the time. If such an agent is operating in real-time under human supervision, now and then it may be necessary for a human operator to press the big red button to prevent the...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
Association for Uncertainty in Artificial Intelligence
2016
|