Safely Interruptible Agents

@inproceedings{Orseau2016SafelyIA,
  title={Safely Interruptible Agents},
  author={Laurent Orseau and Stuart Armstrong},
  booktitle={UAI},
  year={2016}
}
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 agent from continuing a harmful sequence of actions—harmful either for the agent or for the environment—and lead the agent into a safer situation. However, if the learning agent expects to receive… CONTINUE READING
Highly Cited
This paper has 32 citations. REVIEW CITATIONS

2 Figures & Tables

Topics

Statistics

01020201620172018
Citations per Year

Citation Velocity: 12

Averaging 12 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.