Sotabase

Career

· Research Scientist, OpenAI2024–
· PhD Student in Artificial Intelligence, UC Berkeley2015–

Publications (11)

Automatic Goal Generation for Reinforcement Learning Agents
International Conference on Machine Learning · 2017
555
cited
Reverse Curriculum Generation for Reinforcement Learning
Conference on Robot Learning · 2017
491
cited
Stochastic Neural Networks for Hierarchical Reinforcement Learning
International Conference on Learning Representations · 2016
374
cited
Goal-conditioned Imitation Learning
Neural Information Processing Systems · 2019
259
cited
Sub-policy Adaptation for Hierarchical Reinforcement Learning
International Conference on Learning Representations · 2019
82
cited
Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning
IEEE International Conference on Robotics and Automation · 2020
67
cited
Self-supervised Learning of Image Embedding for Continuous Control
arXiv.org · 2019
55
cited
Which Mutual-Information Representation Learning Objectives are Sufficient for Control?
Neural Information Processing Systems · 2021
42
cited
Capacity planning with competitive decision-makers: Trilevel MILP formulation, degeneracy, and solution approaches
European Journal of Operational Research · 2017
25
cited
Adaptive Variance for Changing Sparse-Reward Environments
IEEE International Conference on Robotics and Automation · 2019
6
cited
The magic of light! An entertaining optics and photonics awareness program
2014
4
cited
Sotabase
Carlos Florensa | Researcher Profile | Sotabase | Sotabase