Harshit Sikchi
Computer Science @ UT Austin
hsikchi
[at]utexas.eduNews
- 09/25/2024: Our Scaling laws study of Direct Alignment Algorithms for RLHF is accepted at NeurIPS 2024.
- 09/04/2024: DILO is accepted at CoRL 2024.
- 01/16/2024: Dual-RL, CPL and SMoRe accepted in ICLR 2024.
- 05/01/2023: I'll be starting as a research intern at Meta AI research working on RL.
- 02/16/2023: Our recent work on Dual RL is now public. Check it our for SOTA algos in RL and IL .
- 01/09/2023: rank-game (Unified approach to learning from preferences and imitations) was featured in the Microsoft Research Blog.
- 10/23/2022: Our work FlowPlan awarded best paper at IROS BADUE 2022.
- 03/10/2022: I'll be starting as a research intern at NVIDIA research working on reinforcement learning.
- 11/07/2021: Our work on model-based RL LOOP nominated for Best Paper at CoRL 2021.
About
I am a PhD student in the Computer Science Department at UT Austin co-advised by Prof. Scott Niekum and Prof. Amy Zhang . I am 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. I am broadly interested in Reinforcement Learning (Theory and Practice) to achieve this goal.
Previously, I was a Master’s student in Computer Science
(2019-20) at the
School of Computer Science, Carnegie Mellon University where I worked at Robot Perceiving and Doing lab advised by Prof. David Held. In the summer of 2020,
I worked
on Imitative Motion Planning at Uber ATG . I
worked on
Reinforcement Learning for large action spaces during my prior internship at NVIDIA and spent some time at ETH Zurich working on Semantic Segmentation.
Prior to this, I received my Bachelor’s degree from the Department of Computer Science at the Indian
Institute of
Technology, Kharagpur. My studies at IIT Kharagpur were supported by the Aditya Birla Scholarship (2015-19).
I spent most of time at IIT Kharagpur
working on
Autonomous cars at the Autonomous Ground Vehicle
Lab under the
supervision of Professor Debashis Chakravarty. I led the perception and planning effort-working on
Lane Detection,
Frenet Planner, Hybrid A* Planner, and Segmentation. I completed my bachelor thesis on Safe Reinforcement
Learning with
Prof. Pabitra Mitra. In my spare
time, I enjoy playing tennis, badminton, skiing, running, hiking, and traveling.
Talks, Teaching and Reviewing
Invited Talks2023: Gave a talk on my imitation learning work at Facebook Research (FAIR) and Microsoft Research. |
RL reading group at UT AustinHosting the RL reading group (RLRG) at UT Austin. More details: RLRG Webpage |
ReviewingServing as a Reviewer for RLC 2024, ICML 2024 Workshop proposals, ICML 2024, ICLR 2024, NeurIPS 2023, ICML 2023, ICLR RRL 2023, ICRA 2023, ICLR 2022, ICML 2022, NeurIPS 2022, CoRL 2022, NeurIPS 2022 Offline RL Workshop. |
OrganizingOrganizing the RL beyond Rewards workshop at RL Conference 2024 and Workshop on Models of Human Feedback for AI Alignment at ICML 2024 |
CS394R: Reinforcement Learning: Theory and PracticeTeaching Assistant for Spring 2022. Taught by Prof. Scott Niekum and Prof. Peter Stone |