Search Results for author:
Found 3 papers, 0 papers with code
Neural Physicist: Learning Physical Dynamics from Image Sequences
In this paper, by leveraging recent progresses in representation learning and state space models (SSMs), we propose NeurPhy, which uses variational auto-encoder (VAE) to extract underlying Markovian dynamic state at each time step, neural process (NP) to extract the global system parameters, and a non-linear non-recurrent stochastic state space model to learn the physical dynamic transition.
A Riemannian Primal-dual Algorithm Based on Proximal Operator and its Application in Metric Learning
In this paper, we consider optimizing a smooth, convex, lower semicontinuous function in Riemannian space with constraints.
Riemannian Proximal Policy Optimization
In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems.
