Specifying AI safety problems in simple environments

As AI systems become more general and more useful in the real world, ensuring they behave safely will become even more important. To date, the majority of technical AI safety research has focused on developing a theoretical understanding about the nature and causes of unsafe behaviour. Our new paper builds on a recent shift towards empirical testing (see Concrete Problems in AI Safety) and introduces a selection of simple reinforcement learning environments designed specifically to measure ‘safe behaviours’.

Read on deepmind.google