Active Inference Rule-Learning Simulation (32 trials, 64 agents)

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

• Friston, FitzGerald et al. (2016) — Active inference and learningconcept0.790
  Prior active inference paper providing detailed neurophysiological implementation of belief updates
• This paper may be used as a practical guide on how to implement active inference to simulate experimental behaviour.claim0.788
  Practical utility claimed in abstract and Section 1.
• Active Inferenceframework0.780
  Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.
• Active inference is a normative principle underwriting perception, action, planning, decision-making and learning in biological or artificial agents.quote0.779
• 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.finding0.778
  Group-level simulation result showing generalizability of BMR benefit across agents
• "active inference separates the problems of optimizing action and perception by assuming that action fulfills predictions based on inferred states"quote0.773
• Active Inference agent achieved average score 99.88 [99.64, 100.00] in deterministic FrozenLake environment across 200 trials of 500 episodes.finding0.771
  Table 1, deterministic environment row.
• "Active inference is a self-organising process of action policy selection."quote0.770