Gunjan Paul
Papers
1
Total Citations
2
H-Index
1
About
Gunjan Paul is a researcher at the forefront of intelligent robotics and reinforcement learning, with a particular focus on optimizing autonomous agents for complex, real-world tasks. Their most cited work, "Exploring Performance in Complex Search-and-Retrieve Tasks: A Comparative Analysis of PPO and GAIL Robots" (2024), addresses a critical gap in multi-agent collaboration. By systematically comparing Proximal Policy Optimization (PPO) and Generative Adversarial Imitation Learning (GAIL), Paul’s research provides key insights into how different learning paradigms handle dynamic, goal-oriented environments. This study has already garnered 2 citations, signaling its growing influence in the field. Paul’s contributions are notable for bridging the divide between theoretical reinforcement learning algorithms and practical robotic deployment, offering a nuanced understanding of model cooperation versus individual accuracy. Their work is essential reading for students and researchers developing autonomous systems for search-and-rescue, warehouse logistics, or any domain requiring adaptive, collaborative robots.
Research Focus
Key Achievements
Top Papers
- 1