Little Exploration is All You Need

no code implementations • 26 Oct 2023 • Henry H. H. Chen, Jiaming Lu

The prevailing principle of "Optimism in the Face of Uncertainty" advocates for the incorporation of an exploration bonus, generally assumed to be proportional to the inverse square root of the visit count ($1/\sqrt{n}$), where $n$ is the number of visits to a particular state-action pair.

Thompson Sampling