Sotabase

Career

· Graduate Student Instructor (GSI) - CS184/284A, University of California, Berkeley2025–
· Research Intern, Amazon FAR2021–2022
· PhD Student, University of California, Berkeley2021–
· Research Intern, Google Brain2020–2021
· Research Intern, Amazon
· Bachelor of Science in Aerospace, Aeronautical and Astronautical Engineering, University of California, Berkeley
· Graduate Student, University of Central Florida

Publications (17)

DayDreamer: World Models for Physical Robot Learning
Conference on Robot Learning · 2022
417
cited
Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
165
cited
Visual-Locomotion: Learning to Walk on Complex Terrains with Vision
Conference on Robot Learning · 2021
93
cited
Video Prediction Models as Rewards for Reinforcement Learning
Neural Information Processing Systems · 2023
89
cited
Barkour: Benchmarking Animal-level Agility with Quadruped Robots
arXiv.org · 2023
76
cited
Learning a Diffusion Model Policy from Rewards via Q-Score Matching
International Conference on Machine Learning · 2023
68
cited
Autonomously Untangling Long Cables
Robotics: Science and Systems · 2022
26
cited
A Factor-Graph Approach for Optimization Problems with Dynamics Constraints
arXiv.org · 2020
22
cited
Zero-Shot Terrain Generalization for Visual Locomotion Policies
arXiv.org · 2020
19
cited
Learning Agile Locomotion Skills with a Mentor
IEEE International Conference on Robotics and Automation · 2020
17
cited
GaussGym: An open-source real-to-sim framework for learning locomotion from pixels
arXiv.org · 2025
10
cited
Learning Robotic Locomotion Affordances and Photorealistic Simulators from Human-Captured Data
Conference on Robot Learning · 2024
3
cited
The Design of the Barkour Benchmark for Robot Agility
IEEE/RJS International Conference on Intelligent RObots and Systems · 2024
1
cited
Exploration of Locally-Induced Waves
2020
Learning Visual-Locomotion Policies that Generalize to Diverse Environments
2020
Neural USD: An object-centric framework for iterative editing and control
arXiv.org · 2025
Nonlinear Dynamics Final Project Write-up: Locally Forced Surface Waves
2020
Sotabase
Alejandro Escontrela | Researcher Profile | Sotabase | Sotabase