Temporal Discounting

In active inference, distant future predictions are naturally less precise, leading to Bayes-optimal discounting without an explicit discount factor.

Neighborhood — ranked by edge-count

paper

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.

Temporal discounting emerges naturally from active inference without an explicit discount factor, because predictions in the distant future are less precise.claim0.779
§2, discussion of precision.
Temporal Difference Errorconcept0.742
The formal RL quantity whose signed character is identified with valence in the paper's account
Temporal Permutation Controlmethod0.730
Control procedure that permutes the concatenation order of (C)ARR while preserving internal token order; repeated 10 times.
Interaction over Timeconcept0.702
A sequence of context-response pairs where each context includes the preceding sequence, formalising LM dialogue dynamics.
Temporal embeddingmethod0.696
Lagged time series used to capture dynamical dependencies.
Representational Timeframework0.696
A new kind of time with past/present/future that co-originates with life, enabling memory, anticipation and learning.
Memory As Inter Temporal Communicationframework0.694
Deep Temporal Modelsconcept0.693
Hierarchical generative models with separate timescales, enabling long-term planning.