This work extends the ideas from the two papers of Mehta et al. :
- V. Mehta et al. - An Experimental Design Perspective on Model-Based Reinforcement Learning (ICLR 2022)
- V. Mehta et al. - Exploration via Planning for Information about the Optimal Trajectory (NeurIPS 2022)
The proposed implementation is based on V. Mehta et al. repository. Notably, it adds type-hinting support, and it is available as a python package.