Predictive state representation

Known as: PSR 
In computer science, a predictive state representation (PSR) is a new way to model a state of controlled dynamical system from a history of actions… (More)
Wikipedia

Topic mentions per year

Topic mentions per year

1968-2017
0102019682017

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2015
2015
We study the use of Predictive State Representation (PSR) for modeling of an in-hand manipulation task through interaction with… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
2014
2014
Predictive State Representations (PSRs) are dynamical systems models that keep track of the system's state using predictions of… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
Is this relevant?
2013
2013
Learning accurate models of agent behaviours is crucial for the purpose of controlling systems where the agents’ and environment… (More)
  • figure 1
Is this relevant?
Highly Cited
2010
Highly Cited
2010
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain… (More)
  • figure 1
  • figure 2
Is this relevant?
2006
2006
Recent work on predictive state representation (PSR) models has focused on using predictions of the outcomes of open-loop action… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
Is this relevant?
2006
2006
Predictive state representations (PSRs) are powerful models of non-Markovian decision processes that differ from traditional… (More)
  • figure 1
  • table 1
  • figure 2
Is this relevant?
2004
2004
Predictive state representation (PSR) models for controlled dynamical systems have recently been proposed as an alternative to… (More)
  • table 1
  • figure 1
Is this relevant?
2003
2003
Predictive state representations (PSRs) use predictions of a set of tests to represent the state of controlled dynamical systems… (More)
  • figure 1
  • figure 2
  • table 1
  • table 2
Is this relevant?
2003
2003
We address the problem of optimally controlling stochastic environments that are partially observable. The standard method for… (More)
  • figure 1
Is this relevant?
Highly Cited
2001
Highly Cited
2001
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future… (More)
  • figure 1
  • figure 2
Is this relevant?