AI Safety Workshop: Analyzing a Malicious RL Agent

​Ever wonder how an AI agent could be malicious? Have trained some basic neural nets but don't know anything about reinforcement learning? We'll be diving into a gentle introduction of how an AI agent trained to play a simple game can be perfectly safe during training and then be very dangerous during production.

​For more details, please see https://aisafetyawarenessfoundation.org/workshops/nyc-dec-2024-1/