Acknowledgements

Acknowledgements

I would like to thank my Master’s advisor David Picard for his invaluable help during this project. Additionally, I would like to thank Marie-Morgane Paumard and Loïc Bachelot for explaining their works.

This article was prepared using the Distill template and especially this modified version from the authors of Learning to Predict Without Looking Ahead: World Models Without Forward Prediction.

Citation

For attribution in academic contexts, please cite this work as

Johan Gras,

"Puzzle Reassembly using Model Based Reinforcement Learning", 2019.

BibTeX citation

@article{modelbasedrlpuzzlereassembly2019,
  author = {Johan Gras},
  title  = {Puzzle Reassembly using Model Based Reinforcement Learning},
  url    = {https://johan-gras.github.io/projects/puzzlereassembly/},
  note   = "\url{https://johan-gras.github.io/projects/puzzlereassembly/}",
  year   = {2019}
}

Open Source Code

Our code is not yet release, will be there soon!