AI Safety Camp 2022 project
In AI Safety Camp 2022 I worked on learning and penalizing betrayal in agent communications in an RL setting. A workshop paper describing research work and empirical outcomes can be found here.
Nikiforos Pittaras
In AI Safety Camp 2022 I worked on learning and penalizing betrayal in agent communications in an RL setting. A workshop paper describing research work and empirical outcomes can be found here.