Dynamic Action Inference with Recurrent Spiking Neural Networks

Traub, Manuel; Butz, Martin V.; Legenstein, Robert; Otte, Sebastian

doi:10.1007/978-3-030-86383-8_19

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model of the agent and task dynamics is learned either implicitly (model-free) [14] or explicitly (model-based) [8,27] from experience. The advantage of an explicit generative world model is that it can be used for planning [22], related to model predictive control, or generating training data via imagining [8,27]. Learning and updating such world models, however, can be comparatively expensive and slow.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Policies for Continuous Control via Transition Models

Justus¹,

Thill²,

Gerven³

et al. 2022

Preprint

View full text Add to dashboard Cite

It is doubtful that animals have perfect inverse models of their limbs (e.g., what muscle contraction must be applied to every joint to reach a particular location in space). However, in robot control, moving an arm's end-effector to a target position or along a target trajectory requires accurate forward and inverse models. Here we show that by learning the transition (forward) model from interaction, we can use it to drive the learning of an amortized policy. Hence, we revisit policy optimization in relation to the deep active inference framework and describe a modular neural network architecture that simultaneously learns the system dynamics from prediction errors and the stochastic policy that generates suitable continuous control commands to reach a desired reference position. We evaluated the model by comparing it against the baseline of a linear quadratic regulator, and conclude with additional steps to take toward human-like motor control.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This can be extended to also learn priors about preferred states and actions [8,27,14,23,9,3,4]. Generative models (and their priors) can then be utilized for perception, action, planning [9,22], and the generation of imagined training data [8,27].…”

Section: Related Workmentioning

confidence: 99%