Research talk: Maia Chess: A human-like neural network chess engine
Even when machine learning surpasses human ability in a domain, there are many reasons why AI systems that capture human-like behavior would be desirable. For example, humans may want to learn and collaborate, or humans may need to interact with independent AI agents. A first step in aligning AI agents’ behavior to that of humans is creating agents that better understand human behavior. University of Toronto PhD student Reid McIlroy-Young will present his work, done in collaboration with Microsoft Research, building neural chess engines that can predict human behavior at different skill levels. Furthermore, these engines can be calibrated to target the decisions of specific players via fine-tuning. He will first discuss the value of studying the intersection of human and AI, and the results. He will also discuss where reinforcement learning was outperformed by a classification approach and conclude with a look at the benefits of having research that can be understood by a wide audience.
Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit (opens in new tab)
- 轨迹:
- Reinforcement Learning
- 日期：
- 演讲者：
- Reid McIlroy-Young
- 所属机构：
- University of Toronto
-
-
Reid McIlroy-Young
PhD student, University of Toronto
-
-
Reinforcement Learning
-
-
-
Research talk: Reinforcement learning with preference feedback
Speakers:- Aadirupa Saha
-
-
-
-
-
-
Panel: Generalization in reinforcement learning
Speakers:- Mingfei Sun,
- Roberta Raileanu,
- Harm van Seijen
-
-
Research talk: Successor feature sets: Generalizing successor representations across policies
Speakers:- Kiante 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
-
