My research interest lies in the intersection of Deep Reinforcement Learning and Computer Vision. I am currently working towards intelligent agents that learn from visual observation and can transfer it's learning to take optimal decisions in previously unseen variations of the tasks. I aim to push the boundaries of what reinforcement learning agents can achieve by enabling robust sequential decision making, unlocking their potential to operate in complex, diverse, and dynamic real-world environments. I believe effective representation learning is the way forward. I am interested to explore the delicate balance between exploration and exploitation, as well as the role of memory and transfer learning in promoting generalization.
My previous works include image/video classification, image synthesis using generative adversarial network (GAN), meta-learning, and domain adaptation. In terms of application, my research contributes to intelligent agents, multi-agent system, agriculture (plant disease detection, cattle face recognition, pesticide spraying robot), sports safety (risky tackle detection), crisis-response (summarization of disaster news).
I will be on the job market from the upcoming academic year (2023-2024). Please reach out if you think I will be a good fit for your open position. Thanks for visiting my site.