Concrete Problems in AI Safety
Fast progress and recent developments in the areas of machine learning and AI draws attention to potential influence of AI on our society. One of the identified problems are accidents in systems with integrated machine learning.
At the seminar, we will discuss a recent paper "Concrete Problems in AI Safety" that studies this problem in detail.
Speaker: Ekaterina Koshchenko.
Presentation language: Russian.
Date and Time: April 23rd, 18:30-20:00.
Place: Times, room 204.
Videos from previous seminars are available at http://bit.ly/MLJBSeminars
- About seminars
18 May 2020The AI Economist
11 May 2020Self-Tuning Deep Reinforcement Learning
27 April 2020Sample Efficiency in RL
20 April 2020Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors
13 April 2020AlphaGo to MuZero. Победа компьютера над человеком в интеллектуальных играх.