Fireside chat: Opportunities and challenges in human-oriented AI
A key challenge in developing novel AI technology is to ensure that resulting approaches and their applications fit well within the human environments they will be applied in. Recent research at Microsoft develops new approaches and insights into how AI techniques like machine learning and reinforcement learning can model more human-like AI behavior and provide new insights, experiences, and learning opportunities in game settings. In this fireside chat, Principal Researcher Siddhartha Sen (Microsoft Research NYC) and Senior Principal Researcher Katja Hofmann (Microsoft Research Cambridge) will discuss how their teams’ respective work on Maia Chess and Project Paidia pave the way for more human-aware AI—and where they see exciting opportunities and key challenges on the road to human-compatible AI.
Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit (opens in new tab)
- Track:
- Reinforcement Learning
- Date:
- Speakers:
- Ashley Llorens, Katja Hofmann, Siddhartha Sen
- Affiliation:
- Microsoft Research Redmond, Microsoft Research Cambridge, Microsoft Research NYC
-
-
Ashley Llorens
Corporate Vice President and Managing Director, Microsoft Research
-
Katja Hofmann
Senior Principal Research Manager and lead of the Microsoft Research Game Intelligence team
-
Siddhartha Sen
Principal Researcher
-
-
Reinforcement Learning
-
Opening remarks: Reinforcement Learning
Speakers:- Katja Hofmann
-
-
Research talk: Reinforcement learning with preference feedback
Speakers:- Aadirupa Saha
-
-
-
Research talk: Maia Chess: A human-like neural network chess engine
Speakers:- Reid McIlroy-Young
-
-
Research talk: Making deep reinforcement learning industrially applicable
Speakers:- Jiang Bian,
- Tie-Yan Liu
-
Panel: Generalization in reinforcement learning
Speakers:- Mingfei Sun,
- Roberta Raileanu,
- Harm van Seijen
-
-
Research talk: Successor feature sets: Generalizing successor representations across policies
Speakers:- Kianté Brantley
-
Research talk: Towards efficient generalization in continual RL using episodic memory
Speakers:- Mandana Samiei
-
Research talk: Breaking the deadly triad with a target network
Speakers:- Shangtong Zhang
-
Panel: The future of reinforcement learning
Speakers:- Geoff Gordon,
- Emma Brunskill,
- Craig Boutilier
-
