Planning as inference.

By Matthew Botvinick, Marc Toussaint. 2012

347 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Developmental and Educational Psychology, General Decision Sciences, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Developmental and Educational Psychology

In General Decision Sciences

In Reinforcement Learning

Citations in the corpus

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review (2018, methodology): “The formulation described by Botvinick and Toussaint (2012) does not use the exponential reward transformation, and corresponds more closely to the “pseudo-likelihood” formulation outlined in Section 5.2.”
Compress and Control (2014, background): “These ideas have been recently explored in both the neuroscience (Botvinick and Toussaint 2012; Solway and Botvinick 2012) and machine learning (Attias 2003; Poupart, Lang, and Toussaint 2011) literature.”
Human Replay Spontaneously Reorganizes Experience (2019, background): “The ability to recombine knowledge during replay may allow disparate observations to be compiled into meaningful episodes online (Botvinick and Toussaint, 2012; Pezzulo et al., 2014).”
A free energy principle for a particular physics (2019, background): “…– akin to homoeostasis (Ashby, 1947; Bernard, 1974) and (ii) deep, long-term, active inference – that speaks to planning and allostasis (Attias, 2003; Botvinick and Toussaint, 2012; Ramsay and Woods, 2014; Stephan et al., 2016; Sterling and Eyer, 1988; Sutton et al., 1999; Toussaint and Storkey,…”
Active inference and epistemic value (2015, background): “This allows one to frame goals and preferences in terms of prior beliefs, such that goals are subsequently fulfilled by action (Botvinick & Toussaint, 2012; Kappen, Gomez, & Opper, 2012; Toussaint & Storkey, 2006).”
The free energy principle made simpler but not too simple (2022, neutral): “, policies) that entail a description of planning as inference [120, 121, 122].”
Active Inference, Curiosity and Insight (2017, methodology): “We chose abstract rule learning to illustrate how conceptual knowledge could be accumulated through experience (Botvinick & Toussaint, 2012; Zhang & Maloney, 2012; Koechlin, 2015) and how implicit Bayesian belief updating can be accelerated by applying Bayesian principles not to sensory samples but…”
Noise as a Resource for Computation and Learning in Networks of Spiking Neurons (2014, background): “Several recent reviews present arguments which support the hypothesis that the brain does, in fact, carry out probabilistic inference [34], [38], [51], [71], [73], [74].”