Showing 2019Show all
2 papers · 1 filter
cs.LG2019
Influence-aware Memory Architectures for Deep Reinforcement Learning
Miguel Suau, Jinke He, Elena Congeduti +3
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the…
math.DS2019
Rigorous numerics for a singular perturbation problem
Aleksander Czechowski
Fast-slow systems are notoriously difficult to analyze with rigorous numerics, since the qualitative properties of the solution space change fundamentally when the so-called small…