observation model
Spectral Learning for Infinite-Horizon Average-Reward POMDPs
We address the learning problem in the context of infinite-horizon average-reward POMDPs. Traditionally, this problem has been approached using Spectral Decomposition (SD) methods applied to samples collected under non-adaptive policies, such as uniform or round-robin policies. Recently, SD techniques have been extended to accommodate a restricted class of adaptive policies such as memoryless policies. However, the use of adaptive policies has introduced challenges related to data inefficiency, as SD methods typically require all samples to be drawn from a single policy. In this work, we propose Mixed Spectral Estimation, which generalizes spectral estimation techniques to support a broader class of belief-based policies.
Policy Gradient With Value Function Approximation For Collective Multiagent Planning
Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau
Neural Information Processing Systems http://nips.cc/
Composing graphical models with neural networks for structured representations and fast inference
Matthew Johnson, David K. Duvenaud, Alex Wiltschko, Ryan P. Adams, Sandeep R. Datta
Neural Information Processing Systems http://nips.cc/
Linear dynamical neural population models through nonlinear embeddings
Yuanjun Gao, Evan W. Archer, Liam Paninski, John P. Cunningham
Neural Information Processing Systems http://nips.cc/
Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
Modularity is a critical design principle for both software systems and artificial intelligence (AI).
Online POMDP Planning with Anytime Deterministic Guarantees
Autonomous agents operating in real-world scenarios frequently encounter uncertainty and make decisions based on incomplete information.
Decentralized sketching of low rank matrices
Rakshith Sharma Srinivasa, Kiryung Lee, Marius Junge, Justin Romberg
A fundamental structural model for data is that the data points lie close to an unknown subspace, meaning that the matrix created by concatenating the data vectors has low rank. We address a particular low-rank matrix recovery problem where we wish to recover a set of vectors from a low-dimensional subspace after they have been individually compressed (or "sketched").