Scholar
Rafael Mitkov Rafailov
Google Scholar ID: TwABcRgAAAAJ
Graduate Student, Stanford University
Citations & Impact
Citations
10,849
H-index
26
i10-index
35
Publications
20
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- January 2022: Paper 'Vision-Based Manipulators Need to Also See from Their Hands' elected for an Oral presentation at ICLR; September 2021: Two papers accepted at NeurIPS 2021; March 2021: Paper 'Offline Reinforcement Learning from Images with Latent Space Models' selected for an Oral presentation at L4DC; March 2021: Gave a talk at Intel AI on scaling offline model-based Reinforcement Learning.
Research Experience
- Former Junior Portfolio Manager at Goldman Sachs' Quantitative Investment Strategies (QIS) unit; Part of the Stanford Artificial Intelligence Laboratory (SAIL); Research interests lie at the intersection of machine learning, perception, and control for robotics, specifically deep reinforcement learning, imitation learning, and meta-learning.
Education
- Ph.D. student in Computer Science at Stanford University; Masters degrees in Statistics and Computer Science (with distinction in research) also at Stanford; Graduated from UC Berkeley with highest honors in Applied Mathematics, Statistics, and Economics.
Background
- Interested in the capability of robots and other agents to develop broadly intelligent behavior through learning and interaction. Focused on a data-driven approach to embodied AI, aiming to re-use previously collected data for offline reinforcement, planning, and imitation learning, particularly in realistic domains. Also interested in model-based learning, generative modeling, and real-world deployment of RL.
Miscellany
- Contact: rafailov at cs dot stanford dot edu; Google Scholar, Semantic Scholar, Twitter
Co-authors