Dhruv Malik

About

Dhruv Malik is a leading researcher at the intersection of artificial intelligence and human-robot interaction, with a primary focus on the critical challenge of value alignment. His work seeks to ensure that AI systems correctly identify and act according to their human users’ true objectives. Malik’s most influential contribution is his 2019 paper, “Pragmatic-Pedagogic Value Alignment,” which has garnered 16 citations and reframes the alignment problem by modeling human teachers as pragmatic communicators and AI learners as pragmatic interpreters. This work builds on his earlier research, “An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning” (2018), which formalized value alignment as a two-player cooperative game between a human and a robot. By developing more efficient algorithms for this framework, Malik has advanced the practical feasibility of teaching robots complex human values. His research is foundational for creating AI that can robustly infer and act upon human preferences, making him a key voice in the safe and beneficial deployment of autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Pragmatic-Pedagogic Value Alignment

   16 citations · 2019
2. 2
   An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

   4 citations · 2018

Key Collaborators

Contact & Links