Connect
- GitHub
- Website
Siphelele Danisa
Siphelele did an investigation into the balance between exploration and exploitation for his third year project. His honours research was on scaling and the structure of neural networks, which was an investigation into possible connections between deep learning and the renormalisation group. Currently he is doing research on Multiagent Reinforcement learning focusing more on inference.
- 3rd year project: An Investigation into the Balance Between Exploration and Exploitation in Reinforcement Learning
- Honours project: Scaling and the Structure of Neural Networks, An Investigation into Possible Connections between Deep Learning and the Renormalisation Group
- Masters thesis: Learning to Coordinate Efficiently through Multiagent Soft Q-Learning in the presence of Game-Theoretic Pathologies