Mohit Mittal
Papers
1
Total Citations
1
H-Index
1
About
Mohit Mittal is at the forefront of advancing safe and reliable artificial intelligence for robotics, with a primary focus on uncertainty-aware deep reinforcement learning. His work addresses a critical gap in deploying AI in mission- and safety-critical environments: the need for models that can quantify and act upon their own uncertainty. In his highly cited 2025 paper, Mittal introduces a novel statistical framework that integrates calibrated quantile regression with evidential learning, enabling deep reinforcement learning agents to distinguish between aleatoric (data-driven) and epistemic (model-driven) uncertainties. This breakthrough allows robots to make more cautious, informed decisions when faced with unfamiliar or noisy data, directly enhancing operational safety. While his research is still emerging, with a growing citation footprint, Mittal’s contributions are already shaping a new generation of robust, uncertainty-aware algorithms. His work is particularly notable for its practical applicability, bridging the gap between theoretical uncertainty quantification and real-world robotic control, and positions him as a rising leader in the quest for trustworthy autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1