Particle filtering is a popular method for inferring latent states in stochastic dynamical systems, whose theoretical properties have been well studied in machine learning and statistics communities. In many control problems, e.g., partially observed linear dynamical systems (POLDS), oftentimes the inferred latent state is further used for planning at each step. This paper initiates a rigorous study on the efficiency of particle filtering for sequential planning, and gives the first particle complexity bounds. Though errors in past actions may affect the future, we are able to bound the number of particles needed so that the long-run reward of the policy based on particle filtering is close to that based on exact inference. In particular, we show that, in stable systems, polynomially many particles suffice. Key in our proof is a coupling of the ideal sequence based on the exact planning and the sequence generated by approximate planning based on particle filtering. We believe this technique can be useful in other sequential decision-making problems.
DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs
Tsinghua University（清华大学）；Stanford University（斯坦福大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Institute for Advanced Study（高等研究院）；Massachusetts Institute of Technology（麻省理工学院）
KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
ETH Zürich（苏黎世联邦理工学院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Eindhoven University of Technology（埃因霍温理工大学）；Phillips Research（飞利浦研究院）；Weizmann Institute of Science（魏茨曼科学研究所）
Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models
University of Haifa（海法大学）；ETH Zürich（苏黎世联邦理工学院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Eindhoven University of Technology（埃因霍温理工大学）；Phillips Research（飞利浦研究院）；Weizmann Institute of Science（魏茨曼科学研究所）
Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
University of Alberta（阿尔伯塔大学）；UT Austin（德克萨斯大学奥斯汀分校）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Google DeepMind（谷歌DeepMind）；Georgia Tech（佐治亚理工学院）
