Sotabase

Career

· Research Scientist, DeepMind2019–
· Professor, Center for Human-Compatible Artificial Intelligence (CHAI)2016–
· Chief Scientist, Cogitai, Inc.2015–
· Toyota Professor of Artificial Intelligence, University of Michigan2008–
· Bachelor of Technology in Electrical and Electronics Engineering, Indian Institute of Technology, Delhi1984–1987
· Research Scientist, AT&T Labs
· Associate Professor, University of Michigan
· PhD Student, University of Michigan

Publications (67)

Reward is enough
Artificial Intelligence · 2021
508
cited
Self-Imitation Learning
International Conference on Machine Learning · 2018
276
cited
Mastering the game of Stratego with model-free multiagent reinforcement learning
Science · 2022
250
cited
Behaviour Suite for Reinforcement Learning
International Conference on Learning Representations · 2019
201
cited
In-context Reinforcement Learning with Algorithm Distillation
International Conference on Learning Representations · 2022
174
cited
Discovering Reinforcement Learning Algorithms
Neural Information Processing Systems · 2020
141
cited
Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles
International Conference on Artificial Intelligence and Statistics · 2019
140
cited
Structured State Space Models for In-Context Reinforcement Learning
Neural Information Processing Systems · 2023
131
cited
A Definition of Continual Reinforcement Learning
Neural Information Processing Systems · 2023
113
cited
A Self-Tuning Actor-Critic Algorithm
Neural Information Processing Systems · 2020
100
cited
On the Expressivity of Markov Reward
Neural Information Processing Systems · 2021
97
cited
The Value Equivalence Principle for Model-Based Reinforcement Learning
Neural Information Processing Systems · 2020
90
cited
Discovery of Useful Questions as Auxiliary Tasks
Neural Information Processing Systems · 2019
88
cited
Meta-Gradient Reinforcement Learning with an Objective Discovered Online
Neural Information Processing Systems · 2020
87
cited
What Can Learned Intrinsic Rewards Capture?
International Conference on Machine Learning · 2019
86
cited
Self-Imitation Learning by Planning
IEEE International Conference on Robotics and Automation · 2021
85
cited
Reward is enough for convex MDPs
Neural Information Processing Systems · 2021
81
cited
Bootstrapped Meta-Learning
International Conference on Learning Representations · 2021
60
cited
Generative Adversarial Self-Imitation Learning
arXiv.org · 2018
60
cited
Discovering Evolution Strategies via Meta-Black-Box Optimization
International Conference on Learning Representations · 2022
58
cited
Sotabase