Sreejith Balakrishnan
Papers
1
Total Citations
7
H-Index
1
About
Sreejith Balakrishnan is a researcher advancing the frontiers of inverse reinforcement learning (IRL) and Bayesian optimization, with a focus on making AI systems more interpretable and aligned with human intent. His most cited work, "Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization" (2020, 7 citations), tackles the fundamental ill-posedness of IRL—where multiple reward functions can explain the same observed behavior. By introducing Bayesian optimization to efficiently explore the space of possible rewards, Balakrishnan provides a principled method for resolving ambiguity in learning from demonstration, a critical challenge for value alignment and robot learning. This contribution bridges probabilistic modeling and decision-making, offering a tractable approach to inferring human preferences with fewer samples. His work has implications for safe AI deployment, particularly in scenarios where understanding the true reward structure is essential for trustworthy autonomous systems. Balakrishnan’s research stands out for its theoretical rigor and practical relevance, positioning him as a thoughtful contributor to the growing field of human-aware AI.
Research Focus
Key Achievements
Top Papers
- 1