This paper considers solving a class of nonconvex-strongly-convex distributed stochastic bilevel optimization (DSBO) problems with personalized inner-level objectives. Most existing algorithms require computational loops for hypergradient estimation, leading to computational inefficiency. Moreover, the impact of data heterogeneity on convergence in bilevel problems is not explicitly characterized yet. To address these issues, we propose LoPA, a loopless personalized distributed algorithm that leverages a tracking mechanism for iterative approximation of inner-level solutions and Hessian-inverse matrices without relying on extra computation loops. Our theoretical analysis explicitly characterizes the heterogeneity across nodes (denoted by $b$), and establishes a sublinear rate of $\mathcal{O}( {\frac{1}{{{{\left( {1 - \rho } \right)}}K}}\!+ \!\frac{{(\frac{b}{\sqrt{m}})^{\frac{2}{3}} }}{{\left( {1 - \rho } \right)^{\frac{2}{3}} K^{\frac{2}{3}} }} \!+ \!\frac{1}{\sqrt{ K }}( {\sigma _{\operatorname{p} }} + \frac{1}{\sqrt{m}}{\sigma _{\operatorname{c} }} ) } )$ without the boundedness of local hypergradients, where ${\sigma _{\operatorname{p} }}$ and ${\sigma _{\operatorname{c} }}$ represent the gradient sampling variances associated with the inner- and outer-level variables, respectively. We also integrate LoPA with a gradient tracking scheme to eliminate the impact of data heterogeneity, yielding an improved rate of ${{\mathcal{O}}}(\frac{{1}}{{ (1-\rho)^2K }} \!+\! \frac{1}{{\sqrt{K}}}( \sigma_{\rm{p}} \!+\! \frac{1}{\sqrt{m}}\sigma_{\rm{c}} ) )$. The computational complexity of LoPA is of ${{\mathcal{O}}}({\epsilon^{-2}})$ to an $\epsilon$-stationary point, matching the communication complexity due to the loopless structure, which outperforms existing counterparts for DSBO. Numerical experiments validate the effectiveness of the proposed algorithm.

This paper studies the online reward poisoning problem, wherein an adversary deliberately manipulates the reward function during training to mislead the learning agent into adopting a mischievous policy. While the majority of existing reward poisoning research focuses on offline attacks, which assume prior knowledge of the transition probability, our work explores a more practical yet challenging dynamics-agnostic scenario. Specifically, we consider the scenario where the adversary has access to the agent’s replay buffer and can modify the reward data without the knowledge of transition probabilities. We formalize the poisoning task as an optimization problem and employ a reformulation method to circumvent the double-sampling issue. The proposed algorithm is provably convergent in the tabular setting and can be extended to the function approximation setting, where the poisoned reward network and the poisoned Q-value network are jointly learned to solve the problem. The algorithm’s effectiveness is validated through four distinct experimental evaluations.