Notation. Verifiers, evidence, rollout groups, and group statistics [ftip-0043]
Notation. Verifiers, evidence, rollout groups, and group statistics [ftip-0043]
Let \(\mathcal E\) be an evidence space. Write \(\mathsf V\) for a declared verifier, \(e_{\mathrm {ver}}\in \mathcal E\) for its evidence, \(d_{\mathrm {ver}}\in \{0,1\}\) for its decision, and \(R_{\mathrm {ver}}\in \mathbb R\) for the reward derived from that result.
For a prompt \(x\) and group size \(g\geq 2\), write \(\mathbf Y_x=(Y^{(1)},\ldots ,Y^{(g)})\) for a rollout group sampled from the behavior policy. Let \(R_i\) be the reward of member \(i\), \(\bar R\) the group mean, \(S_R\) the group standard deviation, and \(\widehat A_i\) its group-relative advantage.