Machine-translated by Google. Questions are authored in English.
Top

Discussion

What is safe exploration in a planning or learning agent?

  • A.Exploring only when the agent has spare computation available
  • B.Avoiding actions that could lead to unrecoverable states
  • C.Exploring only states the agent has visited before
  • D.Restricting exploration to a bounded region of the space

Answer: B

Where some actions cause permanent harm, an agent must recognise and avoid them while still exploring enough to learn, which is a genuinely difficult requirement. It matters most in physical systems where a mistake damages equipment or people. Visited states, bounded regions and spare capacity are different restrictions. A requirement arising from the consequences of action rather than from the algorithm is one that the algorithm must be extended to respect.

No comment is present. Be the first to comment.
Loading…

Post your comment

Please log in or register to post a comment.