Research Intern
Developed curriculum generation method that improved performance by upto 20% on robotic tasks.
Please complete the CAPTCHA to continue
A concise factual answer block for searchers comparing this professional profile.
Mehul Damani is listed as Ph.D. Candidate at MIT based in Cambridge, Massachusetts, United States. AeroLeads shows a matched LinkedIn profile for Mehul Damani.
Mehul Damani previously worked as Research Intern at New York University and Research Intern at National University Of Singapore. Mehul Damani holds Doctor Of Philosophy - Phd, Computer Science from Massachusetts Institute Of Technology.
Hello! I am a third year Ph.D. student at MIT, where I am advised by Jacob Andreas. My research interests lie at the intersection of reinforcement learning (RL) and large language models (LLMs).I believe that RL and LLMs have the potential to synergistically improve each other. I am very excited by the potential of RL to improve reasoning, math, coding, and other capabilities in LLMs. Similarly, I am also interested in harnessing the common-sense knowledge of LLM’s to bootstrap RL methods. Finally, having worked on multi-agent RL in the past, I am also interested in studying cooperation in multi-agent settings, with a particular focus on understanding how LLM agents can be integrated into and benefit from multi-agent frameworks. Previously, I worked with Lerrel Pinto at NYU on developing automatic curriculum learning methods for RL agents. Before that, I was a part of the MARMot Lab at NUS, where I worked with Guillaume Sartoretti on applying multi-agent reinforcement learning to traffic signal control and multi-agent pathfinding.
A career timeline built from the work history available for this profile.
Developed curriculum generation method that improved performance by upto 20% on robotic tasks.
- Co-authored 4 papers, open-sourced code with 150+ stars on Github - Developed decentralized reinforcement learning solutions for multi agent pathfinding in complex grid-worlds.
Singapore
- Designed and assembled Vertical Take-off and Landing Aircraft (VTOL) using SolidWorks under the guidance of Professor Ng Bing Feng.- Implemented a control system and tuned control parameters using Pixhawk.- Achieved an endurance of 10 minutes using a 6S Lithium Polymer (LIPO) battery and a takeoff weight of 4.2 Kg.
Singapore
- Assisting in development of an Attitude Control & Determination System (ADCS) for a Low Earth Orbit CubeSat called SCOOBI.- Developing a data fusion algorithm to obtain orientation with respect to Earth's inertial frame by using data from fine & core Sun sensors, magnetometers and gyroscope which will later be used to control orientation through reaction.
Singapore
- Launched high altitude helium balloon in Malaysia to get data in near-space region (20-30 km).- Implemented LoRa ( Long Range) to track high altitude balloon at line of sight distances greater than 40 km using a glass fibre antenna.- Programmed Arduino and Micropython to integrate sensors into payload for high altitude balloons.- Assisted in.
Activities and Societies: Leadership Development Programme MAE, American Society of Mechanical Engineers (ASME),
Quick answers generated from the profile data available on this page.
Mehul Damani is listed as Ph.D. Candidate at MIT.
Mehul Damani is based in Cambridge, Massachusetts, United States.
Mehul Damani has worked for New York University, National University Of Singapore, and Nanyang Technological University.
You can use AeroLeads to view verified contact signals for Mehul Damani, including work email, phone, and LinkedIn data when available.
Mehul Damani holds Doctor Of Philosophy - Phd, Computer Science from Massachusetts Institute Of Technology.
Search by job title, company, industry, location, and seniority. Export verified B2B contact data when you need it.
Start free trial Search contactsCheck these profiles if this is not the Mehul Damani you were looking for.