Jan 2019 – Jun 2019 · 5 mos · Mumbai Area, India

• Theoretical proof of convergence for a wrapper reward function that can be used with any RL algorithm with potential advantages. Empirical work to show and compare the convergence and explore advantages.
• Paper accepted in AAMAS'21 as an Extended Abstract http://aamas.csc.liv.ac.uk/Proceedings/aamas2021/pdfs/p1607.pdf
• Paper accepted in the Scaling Up Reinforcement Learning (SURL) workshop held at IJCAI'19.

Jun 2018 – Jul 2018 · 1 mo · Mumbai Area, India

• Optimisation on the D-Wave Quantum Computer at the NASA AMES Research facility.
• Mapping an NP-Complete optimisation problem on to the problem solvable by the D-Wave.
• Programming and solving problems on the D-Wave.

Jul 2018 – Dec 2018 · 5 mos · Hyderabad Area, India

• Work on object detection on a mobile device with extremely less data.
• Developed a technique for generating synthetic data for training and combining with extremely less real data to achieve adequate real world performance.

Jan 2018 – May 2018 · 4 mos · Goa

• Responsible as a teaching assistant for a class of 180 students.
• Created problems for evaluative programming assignments and conducted tutorial sessions that involved programming strategies and algorithmic concepts.

Aug 2017 – Dec 2017 · 4 mos · Goa

• Responsible as a teaching assistant for a class of 70 students.
• Structured and conducted tutorial sessions that involved reinforcement of concepts covered in lectures, mathematical proofs and problem-solving strategies.

May 2016 – Jul 2016 · 2 mos · Bangalore

• Developed a cross platform phone application for taking classroom attendance in universities integrated with the Enterprise Resource Planning (Sun ERP) product the company offers.