Daljeet Nandha
Papers
2
Total Citations
59
H-Index
2
About
Daljeet Nandha is a rising researcher at the intersection of robotics, reinforcement learning, and natural language processing. Their work focuses on enabling robots to acquire complex skills more efficiently and to reason about long-horizon tasks through language. Nandha’s key contributions include the development of the Model Predictive Actor-Critic (MPAC) algorithm, which integrates model predictive control with deep reinforcement learning to accelerate robot skill acquisition while mitigating model-bias—a critical advancement for sample-efficient, real-world robot learning. This work, published in 2021, has already garnered 32 citations, reflecting its impact on the field. More recently, Nandha has pioneered the use of smaller language models for grounded task planning, demonstrating that a finetuned GPT-2 can effectively reason over scene graphs to decompose long-horizon tasks into subgoal specifications. This 2023 study, with 27 citations, opens new avenues for deploying lightweight, interpretable language models in assistive robotics. Nandha’s work bridges model-based RL and language-guided planning, offering practical pathways toward more autonomous and capable service robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2