Emmeran Johnson

collaborators

3 papers

cs.LG2025

Stochastic Shortest Path with Sparse Adversarial Costs

Emmeran Johnson, Alberto Rumi, Ciara Pike-Burke +1

We study the adversarial Stochastic Shortest Path (SSP) problem with sparse costs under full-information feedback. In the known transition setting, existing bounds based on Online…

cs.LG2025

On the necessity of adaptive regularisation:Optimal anytime online learning on $ℓ_{p}$ -balls

Emmeran Johnson, David Martínez-Rubio, Ciara Pike-Burke +1

We study online convex optimization on $ℓ_{p}$ -balls in $R^{d}$ for $p > 2$ . While always sub-linear, the optimal regret exhibits a shift between the high-dimensional setti…

cs.LG2023

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

Emmeran Johnson, Ciara Pike-Burke, Patrick Rebeschini

We theoretically explore the relationship between sample-efficiency and adaptivity in reinforcement learning. An algorithm is sample-efficient if it uses a number of queries $n$ to…

Stochastic Shortest Path with Sparse Adversarial Costs

On the necessity of adaptive regularisation:Optimal anytime online learning on ℓp​-balls

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

On the necessity of adaptive regularisation:Optimal anytime online learning on $ℓ_{p}$ -balls