Anil A. Bharath

About

Anil A. Bharath is a leading researcher at the intersection of artificial intelligence and robotics, with a primary focus on deep reinforcement learning (DRL). His work has been instrumental in advancing the scalability and real-world applicability of DRL, particularly for autonomous systems and robotic manipulation. His seminal survey, "Deep Reinforcement Learning: A Brief Survey," has garnered over 4,200 citations, establishing itself as a foundational reference in the field. Bharath’s contributions extend to developing novel algorithms that enhance learning efficiency and robustness. He has pioneered techniques like Episodic Self-Imitation Learning and Diversity-based Trajectory and Goal Selection, which accelerate training in sparse-reward environments. A key area of his research addresses the critical challenge of transferring agents from simulation to the real world, where he has conducted in-depth analyses of domain randomisation methods to improve agent explainability and reliability. Through his highly cited work and innovative algorithmic contributions, Bharath has significantly shaped modern approaches to building autonomous systems capable of complex, real-world tasks.

Research Focus

Key Achievements

Top Papers

1. 1
   Deep Reinforcement Learning: A Brief Survey

   4,261 citations · 2017
2. 2
   A Brief Survey of Deep Reinforcement Learning

   754 citations · 2017
3. 3
   Analysing deep reinforcement learning agents trained with domain randomisation

   21 citations · 2022
4. 4
   Episodic Self-Imitation Learning with Hindsight

   16 citations · 2020
5. 5
   Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay

   11 citations · 2021
6. 6
   Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation

   7 citations · 2019

Key Collaborators

Contact & Links