FIELD NOTES TOPIC
two-player games
2 notes, newest first.
Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
The paper introduces a method called budget-constrained confidence-scheduled restricted responses (CS-RNR) for safe opponent exploitation in two-player zero-sum imperfect-information games. This method helps an agent…
Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
Researchers propose a new method called Budget-Constrained Confidence-Scheduled Restricted Responses (CS-RNR) for safe opponent exploitation in two-player zero-sum imperfect-information games. The method tracks action…
