finding

active

finding:a-naive-agent-equipped-with-reduced-priors-from-an-experienced-agent-performs-perfectly-with-maximum-confidence-from-the-first-trial

A naive agent equipped with reduced priors from an experienced agent performs perfectly with maximum confidence from the first trial.

Demonstration that model-level priors (not parameter-level knowledge) suffice for immediate transfer

Source paper

extracted_from

Active Inference, Curiosity and Insight

(2017) · Karl Friston · Marco Lin · Chris Frith · Giovanni Pezzulo +2

Neighborhood — ranked by edge-count

Claims (1)

claim

The results of abductive reasoning (reduced model priors) can be communicated to other agents as prior beliefs, provided all agents share the same model lexicon or hypothesis space.
supports
Explanation of how knowledge (not just parameters) is shared between agents; links to pre-Cartesian consciousness

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.

In single-agent simulation of 32 trials, performance becomes perfect after trial 14 without Bayesian model reduction, with confidence increasing progressively.finding0.810
Baseline learning curve for pure epistemic learning without structure learning
What is the nature of the shared model space or lexicon that enables naive agents to properly implement received priors from experienced agents?question0.801
Prerequisite for model-level communication; raises issues of neural hermeneutics
Nearly all of 64 simulated agents attain 100% performance at around the 10th trial when allowed to perform abductive Bayesian model reduction after each trial.finding0.789
Group-level simulation result showing generalizability of BMR benefit across agents
What are the neuronal mechanisms by which prior beliefs from one agent's model are received and properly implemented by a naive agent (neuronal hermeneutics)?question0.788
Open question about inter-agent communication beyond model-space assumption
Single agents can generalize better to unseen tasks because they are not constrained by predefined heuristic-based workflows.claim0.778
Architectural belief motivating single-agent design choice; suggests flexibility provides better out-of-distribution performance.
Once visible, the prior is eliminated via Bayesian model reduction resulting in a post-dual agent with unconstrained QRF deployments.claim0.766
Formal description of the transition to post-duality.
All intelligent agents, regardless of their substrate, can be understood as needing to respond to a perceived mismatch between what is and what should be.claim0.766
Foundation for the SCI loop model.
Simulated agent achieves perfect performance after trial 12 following Bayesian model reduction (sleep), versus ~14 trials without BMR.finding0.765
Key result showing BMR dramatically accelerates rule learning in simulation