Anand Balakrishnan

Southern California University for Professional Studies

Papers

1

Total Citations

14

H-Index

1

About

Anand Balakrishnan is a leading researcher at the intersection of formal methods, control theory, and reinforcement learning (RL), with a primary focus on synthesizing safe and verifiable autonomous systems. His most impactful work, "Model-based Reinforcement Learning from Signal Temporal Logic Specifications" (2020, 14 citations), pioneers a novel framework that replaces traditional, exploitable reward functions with rich, temporal logic specifications. This approach enables RL agents to learn control policies that inherently satisfy complex, time-sensitive behavioral constraints, directly addressing a critical vulnerability in standard reward design. By grounding learning in formal logic, Balakrishnan’s contributions provide a principled method for ensuring that autonomous robots—from drones to manipulators—operate reliably under real-world specifications. His research has been recognized for bridging the gap between theoretical formal verification and practical learning-based control, offering a robust pathway toward trustworthy AI. With a growing citation footprint, Balakrishnan’s work is shaping how next-generation robotic systems are designed to be both adaptive and provably correct, making him a key voice in the advancement of safe reinforcement learning.

Research Focus

Key Achievements

1
H-Index
1
Papers
14
Total Citations
14
Avg Citations/Paper
🏆 Most Cited Paper
Model-based Reinforcement Learning from Signal Temporal Logic Specifications
14 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 2
🏛 Institutions: Southern California University for Professional Studies

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago