Model Predictive Control

Corriou, Jean‐Pierre

doi:10.1007/978-1-4471-3848-8_16

Cited by 1 publication

(1 citation statement)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, as noted above, for a single prediction, the direct perception architecture operates in constant time regardless of how distant a future the prediction needs to be concerned about. While this advantage is nothing new in affordance literature (Zeng et al, 2018), it is worth pointing out that predicting the future has a long history where conventional approaches of predicting future valence, such as in model-based control, usually can be very difficult to scale computationally since they rely on model-based or sample-based optimization with multi-step roll-outs (Corriou, 2004).…”

Section: Affordances As Gvfsmentioning

confidence: 99%

Affordance as general value function: a computational model

2021

View full text Add to dashboard Cite

General value functions (GVFs) in the reinforcement learning (RL) literature are long-term predictive summaries of the outcomes of agents following specific policies in the environment. Affordances as perceived action possibilities with specific valence may be cast into predicted policy-relative goodness and modeled as GVFs. A systematic explication of this connection shows that GVFs and especially their deep-learning embodiments (1) realize affordance prediction as a form of direct perception, (2) illuminate the fundamental connection between action and perception in affordance, and (3) offer a scalable way to learn affordances using RL methods. Through an extensive review of existing literature on GVF applications and representative affordance research in robotics, we demonstrate that GVFs provide the right framework for learning affordances in real-world applications. In addition, we highlight a few new avenues of research opened up by the perspective of “affordance as GVF,” including using GVFs for orchestrating complex behaviors.

show abstract

Section: Affordances As Gvfsmentioning

confidence: 99%