[DONE] Improving Sample Efficiency in RL: is QPU all you need?

[agercas]

Project Name: Improving Sample Efficiency in RL: is QPU all you need?

Team Name: TheTeam

Which challenges would you like to submit your project for? Hybrid Quantum-Classical Computing Challenge NVIDIA Challenge

Project Link: https://github.com/agercas/QHack2023_QRL/tree/10c14a8ed2e865895120e5316c60466f68eab5f4

Project description: RL is powerful but sample inefficient. We explore ways how QC can improve RL. We implement several algorithms, train a bunch of agents and compare RL and QRL agents. Lastly, we summarize the results and discuss the limitations and future work. Further details in the project readme.