Stephen McAleer

University of California, Irvine

Papers

2

Total Citations

40

H-Index

2

About

Stephen McAleer is a leading researcher in reinforcement learning and robotics, with a focus on enabling machines to achieve human-level dexterity and solve complex, sparse-reward tasks. His major contributions include pioneering work on bimanual dexterous manipulation, where his 2022 paper, "Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning" (29 citations), tackles the high-dimensional challenge of coordinating two robotic hands to perform baby-level manipulation tasks—a critical step toward general-purpose robotics. McAleer also advanced sparse-reward learning with his 2019 study, "Curiosity-Driven Multi-Criteria Hindsight Experience Replay" (11 citations), which integrates curiosity-driven exploration with hindsight methods to overcome failures in complex tasks like multi-block stacking. His work demonstrates how combining intrinsic motivation with algorithmic innovation can push RL beyond toy problems into real-world applications. By addressing fundamental bottlenecks in dexterity and reward design, McAleer’s research has significant implications for autonomous systems, manufacturing, and assistive robotics, earning recognition for bridging the gap between simulation and physical-world performance.

Research Focus

Key Achievements

2
H-Index
2
Papers
40
Total Citations
20
Avg Citations/Paper
🏆 Most Cited Paper
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
29 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: University of California, Irvine

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago