Papers

2

Total Citations

153

H-Index

2

About

Charles Game is a leading researcher at the intersection of robotics and artificial intelligence, with a primary focus on using deep reinforcement learning to enable complex, agile locomotion and manipulation in humanoid robots. His most influential work, “Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning” (2024), has garnered 147 citations and demonstrates a groundbreaking achievement: training a low-cost, 20-actuator miniature humanoid to play simplified one-versus-one soccer. This research proved that deep RL can synthesize sophisticated, safe movement skills that compose into dynamic, real-time behavioral strategies, pushing the boundaries of what is possible with affordable hardware. Game’s contributions are pivotal for advancing autonomous robots capable of operating in unpredictable, human-centric environments. His work not only showcases the practical power of deep RL but also opens new avenues for research in robot sports and dexterous control, making him a key figure in the ongoing effort to create truly agile and intelligent machines.

Research Focus

Key Achievements

2
H-Index
2
Papers
153
Total Citations
77
Avg Citations/Paper
🏆 Most Cited Paper
Learning agile soccer skills for a bipedal robot with deep reinforcement learning
147 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 27
🏛 Institutions: Google DeepMind (United Kingdom), University College London

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago