claim

active

claim:whether-a-state-is-rewarding-or-not-is-a-function-of-the-agent-themselves-and-not-the-environment

Whether a state is rewarding (or not) is a function of the agent themselves, and not the environment.

§1, contrasting RL reward conceptualization.

Source paper

extracted_from

Active inference: demystified and compared

(2021) · Noor Sajid · Philip J. Ball · Thomas Parr · Karl J. Friston

Neighborhood — ranked by edge-count

Communities (1)

community

Active inference & agent ecology
members_of
Free energy minimization, Markov blankets, trust gradients, and multi-agent rhythm/deferral frameworks

Claims (1)

claim

In active inference, reward can simply be treated as another observation we have a preference over, rather than a special signal.
extends
Abstract; central distinction.

Questions (1)

question

How can reward functions be meaningfully specified when the same outcome may be valuable or detrimental depending on context?
gates
Motivates active inference's solution: learning prior preferences from interaction rather than external specification.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

The rewarding and life-enhancing nature of work comes into focus when the thing made has life, and the makers begin to change dramatically.claim0.783
An agent satisfying the sufficient conditions for autonomy (Artemis) need not be a welfare subject.claim0.772
Conclusion from the two premises.
Should an aversive signal be operationalized as direct environmental feedback or as a latent state the agent must infer?question0.771
Design question answered in the paper by choosing latent inference over direct feedback
Active inference agents can learn their own reward function (prior preferences) by interacting with the environment, bypassing the need for an explicit reward signal.claim0.769
Abstract and §3, preference learning section.
acting to optimize value and perception are two aspects of exactly the same principle; namely the minimisation of a quantity [free energy] that bounds the probability of sensory input, given a particular agent or phenotype.quote0.769
Concise statement of the free-energy principle's unification of action and perception.
People do not know—emotionally—how to please themselves. In part, they are prevented by society. And in part, they are prevented by themselves, by their inner thought police.claim0.768
Diagnosis of why living structure is absent from the world: a failure of emotional knowledge enforced by social and internal constraints.
In the absence of external reward, babies and scientists and others explore their world. Using some sort of adaptive predictive world model, they improve their ability to answer questions such as what happens if I do this or that?quote0.767
Schmidhuber (2006) characterization of epistemic curiosity used to frame the paper's approach
Emotion refers to a state concept, so stateful representations in general may be more persistent across tokens.claim0.767
Interpretive hypothesis offered to explain why emotion features are more persistent