DeepMDP: Learning Continuous Latent Space Models for Representation Learning
International Conference on Machine Learning, pp. 2170-2179, 2019.
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this process, we introduce the concept of a DeepMDP, a parameterized latent space model that is trained via the minimization of two tractable losses: prediction of reward...More
PPT (Upload PPT)