RL Researcher · Deep Learning · Computer Vision
B.Tech Mathematics & Computing, Central University of Karnataka (2023–2027)
I work at the intersection of Reinforcement Learning, robotics, and applied Deep Learning. My research focuses on biped locomotion, Obstacle Avoidance, and LLM-guided reward shaping. I enjoy building systems that are both theoretically grounded and practically deployable — from simulation environments to real-time computer vision applications.
Currently working on: LLM-driven RL reward design.
Learning Multi-Skill Locomotion in Underactuated Biped: A Waypoint-Based Reward Shaping Approach
Published — IEEE ICC 2025 (International Peer-Reviewed Conference)
UAV-Assisted Navigation of an Underactuated Biped via Soft Actor-Critic Reinforcement Learning
Under review — IJCAI-ECAI 2026 (Tier-1 AI Conference)
Closed-loop GPT-4 pipeline that autonomously refines RL reward functions across iterations — achieving ~69× improvement in forward locomotion distance and 67% reduction in torso tilt.
GPT-4 SAC PyBullet Gymnasium NumPy
6–8 DOF underactuated biped trained with SAC, TD3, and DDPG over 10M+ steps. Integrated A* global path planning for hierarchical obstacle avoidance — 94% navigation success, 2% fall rate.
PyBullet SAC TD3 DDPG A* Gymnasium
Real-time contactless attendance with a 128-d face encoding pipeline, liveness detection (anti-spoofing via YuNet + custom ONNX model), and a secure admin dashboard with live video streaming.
Flask OpenCV dlib face_recognition ONNX SQLite
Fully connected network built with NumPy only — manual forward/backward propagation, softmax activation, cross-entropy loss, and mini-batch gradient descent. 90%+ test accuracy.
NumPy Matplotlib
Real-time gesture-controlled drawing system using hand landmark detection. Supports drawing, erasing, brush control, and color selection via gesture recognition.
OpenCV MediaPipe NumPy
Languages — Python, C++, JavaScript, SQL, Matlab, R
ML / DL — PyTorch, TensorFlow, Keras, Scikit-learn, NumPy, Pandas
RL / Simulation — Gymnasium, PyBullet, MuJoCo, Isaac Gym
Computer Vision — OpenCV, MediaPipe, dlib, ONNX
Tools — Git, Flask, SQLite, Power BI
Open to research internships, collaborations, and interesting problems in RL, robotics, and deep learning.
