RL algorithms

The different reinforcement learning algorithms used across conditions, to ensure the alignment result is not algorithm-specific.

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.

Reinforcement learning (RL)concept0.840
Machine learning paradigm where agents learn to maximize cumulative reward through interaction.
Causal emergence predictive of final reward early in RL training across multiple algorithms, architectures, and environments.finding0.755
Empirical result: CE measurements correlate with and predict learning performance in RL agents.
Representational dynamics aligned with reward improvement in most RL tasks.finding0.749
Secondary empirical result: CE-based representational changes correlate with task success.
Bjorklund's Algorithmconcept0.747
Algorithm developed for timing systems in neutron accelerators; generates binary sequences where pulses are distributed as evenly as possible among intervals.
Reinforcement Learningframework0.745
Alternative framework for agent behavior; based on reward maximization rather than free energy minimization.
Euclidean Algorithmconcept0.744
Ancient algorithm from Euclid's Elements (circa 300 B.C.) that computes greatest common divisor; shown to structurally parallel Bjorklund's rhythm generation algorithm.
Reinforcement Learning from Human Feedback (RLHF)framework0.741
A competing alignment approach that fine-tunes models based on human evaluator feedback; discussed as complementary to SOO
Evolutionary Algorithmsmethod0.735
Machine learning approach using evolutionary processes to generate and select designs, used to blur the designed vs. evolved distinction