Davin Tjia
Papers
1
Total Citations
4
H-Index
1
About
Davin Tjia is a researcher advancing the frontier of robot learning, with a focus on reducing the human burden in teaching machines new skills. His primary research areas include reinforcement learning, reward function design, and learning from passive visual data. Tjia’s most notable contribution is his work "Rank2Reward: Learning Shaped Reward Functions from Passive Video" (2024), which tackles a critical bottleneck in robotics: the need for expensive, action-labeled demonstrations. By enabling robots to learn effective reward functions from raw, action-free video of tasks being performed, Tjia’s approach dramatically simplifies the data collection process, moving beyond kinesthetic teaching and teleoperation. This work has already garnered 4 citations, signaling its early impact on the community. Tjia’s research is particularly compelling for its potential to democratize robot learning, allowing non-experts to contribute to training data. His focus on human-in-the-loop efficiency and passive data utilization marks him as a promising voice in making robotic skill acquisition more scalable and accessible.
Research Focus
Key Achievements
Top Papers
- 1Rank2Reward: Learning Shaped Reward Functions from Passive Video4 citations · 2024