Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
2
0
0
0
Asynchronous Q-learning's last iterate converges to $\varepsilon$-accuracy in $\widetilde{O}(H^4/(\mu_{\min}\varepsilon^2)+\mathfrak h_\star)$ transitions, with initialization cost additive and independent of the effective horizon.