Aug 2026
This work develops robust decentralized algorithms for each setting and derive regret guarantees that nearly match centralized heavy-tailed rates.
Daphne Feng, Ricardo Parada, Lily Jiang et al.
· arXiv.org · 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
Preprint
Aug 2026
Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown. We consider three information structures: (A)~unobserved actions with common rewards, (B)~observed actions with independent rewards, and (C)~unobserved action...
Ricardo Parada, Chenzhang Zhao, William Chang
· 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
These results provide the first tight regret guarantees for Lipschitz-smooth continuous-time episodic MDPs with Poisson decision epochs.
Kenny Guo, Valentio Iverson, Sahan Wijetunga et al.
· arXiv.org · 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
Conference
Open access
Jul 2026
In this work, we extend the Dependent Click Model (DCM) Bandits to a multiplayer information-asymmetric setting, where multiple agents interact with a shared ranked list and may observe multiple clicks per session, introducing new challenges for selection strategies. We study asymmetry in (1) actions and (2) rewards, p...
Andy Wang, Charlton Shih, William Chang
· 2026 8th Asia Conference on... · 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
Preprint
Aug 2026
Change-of-measure lower bounds show that shared-reward identification is optimal up to one universal logarithmic factor, and that the entire statistical price of removing communication is a multiplicative $\rho^2$ in sample complexity.
Larissa Xu, Jasmine Nguyen, William Chang
· 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓