Thompson Sampling

A Bayesian exploration strategy that samples from the posterior distribution over model parameters to decide actions.

Neighborhood — ranked by edge-count

framework

Bayesian Model-Based Reinforcement Learning
implements
RL variant that maintains beliefs over environment model; compared to active inference using Thompson sampling.

concept

Reinforcement learning (RL)
associated_with
Machine learning paradigm where agents learn to maximize cumulative reward through interaction.

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.

Autoregressive Samplingmethod0.782
The mechanism by which LLMs generate text: drawing a token from the next-token distribution and appending it to context repeatedly
Rejection samplingmethod0.772
A technique to filter model outputs; Redwood Research's project mentioned.
Verbalized Sampling (VS)framework0.741
The paper's proposed training-free prompting strategy that prompts the model to verbalize a probability distribution over a set of responses rather than generating a single response
Monte Carlo Cone Samplingmethod0.737
Procedure for sampling 64 random nonnegative combinations of cone basis vectors to evaluate the full cone distribution
Activation Interval Samplingmethod0.731
Dividing feature activation spectrum into 11 evenly-spaced intervals and sampling uniformly to evaluate monosemanticity across activation levels
Sampled-decoding self-reportmethod0.721
Temperature=0.8 sampled decoding for self-report; reduces collapse moderately but remains discrete and noisy
Nucleus Samplingconcept0.718
Decoding strategy used throughout experiments; p=0.9 selected to increase response diversity
Cross-Modal Samplingmethod0.707
Technique used to demonstrate that the self-prior captures visual–proprioceptive associations by recovering visual appearance from proprioception alone