Internships | Aaryan Sharma

Robotics in the field

Sat, 01 Nov 2025 00:00:00 +0000

At Diligent Robotics, I help keep mobile service robots dependable where it matters most: busy hospitals that cannot afford downtime or ambiguity.

What the work actually looks like

Fleet awareness — tracking robot state, routes, and anomalies so issues are caught early.
Field debugging — isolating whether a failure mode is environmental, software, or hardware-adjacent, then packaging evidence for engineering.
Human interaction — calm, accurate answers for staff (and sometimes visitors) who are meeting automation in a high-stakes setting.

What I took away

Robotics is as much about trust and communication as it is about code. The same discipline I bring to ML—tight feedback loops, careful logging, and honest uncertainty—shows up here in how we operate machines around people.

Deep RL agent for Pong

Thu, 15 Aug 2024 00:00:00 +0000

During my internship at DISCOVERY LAB GLOBAL, I trained an autonomous agent to play and win Pong using deep reinforcement learning and convolutional neural networks in Python.

What I built

A custom simulation to log rewards, frame stacks, and policy rollouts so the team could compare runs quickly.
Training loops with tuned discount factors, learning rates, and exploration schedules to stabilize policy improvement.
A concise technical paper capturing architecture choices, experiments, and lessons learned for stakeholders.

Outcomes

The project sharpened my intuition for credit assignment, sample efficiency, and how engineering choices in the simulator change what the policy can learn—skills I still apply when thinking about data quality and evaluation for ML systems.