Tej Pandit
Papers
1
Total Citations
8
H-Index
1
About
Tej Pandit is a researcher at the forefront of lifelong learning and reinforcement learning, with a focus on building agents that can continuously adapt and improve over time. His most-cited work, "Relational Neurogenesis for Lifelong Learning Agents" (2020, 8 citations), introduces a novel framework that enables reinforcement learning systems to dynamically grow and restructure their neural networks in response to new tasks, effectively overcoming the catastrophic forgetting that plagues traditional models. This contribution is pivotal for creating more robust and scalable AI agents capable of learning across diverse environments without requiring retraining from scratch. Pandit's research emphasizes the potential of reinforcement learning to replace painstakingly curated datasets with continuous, interactive learning, making his work highly relevant for robotics and virtual agent applications. Though his citation count is modest, his innovative approach to neurogenesis and lifelong learning positions him as a promising voice in the quest for truly adaptive artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1Relational Neurogenesis for Lifelong Learning Agents8 citations · 2020