1. Policy Decomposition: Approximate Optimal Control with Suboptimality Estimates
2. Search methods for policy decompositions;Khadke,2022
3. Unsupervised state representation learning in atari;Anand;Advances in Neural Information Processing Systems,2019
4. A geometric perspective on optimal representations for reinforcement learning;Bellemare;Advances in neural information processing systems,2019
5. Deepmdp: Learning continuous latent space models for representation learning;Gelada