AM-PPO modulates GAE advantages with a feedback-controlled tanh gate and reports improved reward trajectories on MuJoCo benchmarks, tested once per configuration.
Split NMSSM from dimensional reduction of a $10D$, $\mathcal{N}=1$, $E_8$ theory over a modified flag manifold
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We review the Standard Model extension that results from the dimensional reduction of a $10D$, $\mathcal{N}=1$, $E_8$ gauge theory over the $M_4 \times SU(3)/U(1) \times U(1) \times \mathbf{Z}_3 $ space, which leads to a $4D$, $\mathcal{N}=1$, $SU(3)^3\times U(1)^2$ theory. Below the unification scale we obtain a Split NMSSM effective theory. The third generation quark and light Higgs masses are within the experimental limits at 2-loop level and the neutralino LSP mass is predicted $<800$ GeV.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AM-PPO: (Advantage) Alpha-Modulation with Proximal Policy Optimization
AM-PPO modulates GAE advantages with a feedback-controlled tanh gate and reports improved reward trajectories on MuJoCo benchmarks, tested once per configuration.