Scholar
Harshit Sikchi
Google Scholar ID: jFOPZE0AAAAJ
Research Scientist, OpenAI
Citations & Impact
Citations
562
H-index
11
i10-index
12
Publications
20
Co-authors
47
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications: RLZero accepted at NeurIPS 2025; Fast Adaptation with Behavioral Foundation Models accepted at RLC 2025; Proto Successor Measure (Unsupervised RL) accepted at ICML 2025; CRESTE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance accepted at RSS 2025; Iterative Dual RL accepted at ICLR 2025; Our Scaling laws study of Direct Alignment Algorithms for RLHF accepted at NeurIPS 2024; DILO accepted at CoRL 2024; Dual-RL, CPL, and SMoRe accepted in ICLR 2024; FlowPlan awarded best paper at IROS BADUE 2022; LOOP nominated for Best Paper at CoRL 2021.
Research Experience
- August 2024: Research Intern at Meta FAIR, Paris, working on Unsupervised RL; May 2023: Research Intern at Meta AI, working on RL; March 2022: Research Intern at NVIDIA, working on RL; Summer 2020: Worked on Imitative Motion Planning at Uber ATG.
Education
- Ph.D. in Computer Science from the University of Texas at Austin, co-advised by Prof. Scott Niekum and Prof. Amy Zhang; M.S. in Computer Science from Carnegie Mellon University (2019-2020), advised by Prof. David Held; B.S. in Computer Science from Indian Institute of Technology, Kharagpur, supported by the Aditya Birla Scholarship (2015-2019), thesis on Safe Reinforcement Learning with Prof. Pabitra Mitra.
Background
- Interested in pushing the limits of Interactive Agent Learning: enabling agents to make the most of limited data and make sense of different sources of information present in the world to improve their ability. Broadly interested in Reinforcement Learning (Theory and Practice). Previously, a Master’s student at Carnegie Mellon University, working at the Robot Perceiving and Doing lab. Worked on Imitative Motion Planning at Uber ATG. Interned at NVIDIA, working on Reinforcement Learning for large action spaces, and spent some time at ETH Zurich working on Semantic Segmentation.
Miscellany
- Personal interests include playing tennis, badminton, skiing, running, hiking, and traveling.
