AJ Miller

Papers

1

Total Citations

2

H-Index

1

About

AJ Miller is a leading researcher at the intersection of reinforcement learning and robotics, with a primary focus on enabling agile, dynamic locomotion for legged systems. His most impactful work introduces MIMOC (Motion Imitation from Model-Based Optimal Control), a novel framework that bridges the gap between model-based and learning-based control. Rather than relying on motion capture data from animals or humans, MIMOC uses reference trajectories generated by model-based optimal control to train a reinforcement learning (RL) controller. This approach allows the robot to learn robust, agile behaviors while avoiding common pitfalls like reward hacking or unnatural gaits. Miller’s work, published in 2023, has already garnered attention for its practical elegance, offering a scalable pathway to deploy RL on real hardware. By combining the precision of optimal control with the adaptability of RL, he has opened new avenues for robots to traverse complex terrains. His contributions are particularly valuable for students and engineers seeking to move beyond simulation into real-world deployment, making him a rising voice in the robotics community.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
Reinforcement Learning for Legged Robots: Motion Imitation from Model-Based Optimal Control
2 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 3

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 10 days ago