Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
The presented work addresses the observation problem for a large class of nonlinear systems, including systems which are nonlinear in the unmeasured states. Assuming partial state ...
A problem of planning for cooperative teams under uncertainty is a crucial one in multiagent systems. Decentralized partially observable Markov decision processes (DECPOMDPs) prov...
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...