Antora Dev
Papers
1
Total Citations
3
H-Index
1
About
Antora Dev is a rising researcher at the intersection of reinforcement learning and nonlinear control systems, with a primary focus on developing data-driven solutions for complex, unstable dynamical systems. Her most-cited work, "Q-Learning Based Control for Swing-Up and Balancing of Inverted Pendulum" (2024, 3 citations), tackles the classic yet formidable challenge of stabilizing an inverted pendulum on a moving cart—a benchmark problem in control theory and robotics due to its inherent instability and highly nonlinear dynamics. By applying a model-free Q-learning algorithm, Dev demonstrates how reinforcement learning can effectively learn swing-up and balancing policies without requiring an explicit system model, offering a robust alternative to traditional control methods. This contribution is particularly significant for advancing adaptive control in robotics and autonomous systems, where environmental uncertainties prevail. Though early in her career, Dev’s work signals a promising trajectory in bridging machine learning with real-world control applications, positioning her as an emerging voice in the growing field of learning-based control.
Research Focus
Key Achievements
Top Papers
- 1Q-Learning Based Control for Swing-Up and Balancing of Inverted Pendulum3 citations · 2024