Research map / Bandits and online learning / Multi-armed bandits
Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DrFed-UCB with graph-history-based weights and delayed-feedback stopping times | Decentralized heterogeneous MAB with sub-Gaussian rewards · Random time-varying graphs | regret upper bound: O(\log T) | Helped |
| Extend DrFed-UCB confidence bounds for sub-exponential rewards | Decentralized heterogeneous MAB · Random time-varying graphs with sub-exponential rewards | regret upper bound: O(\ln{T}) | Helped |
| Use DrFed-UCB's confidence-bound and consensus procedure | Decentralized heterogeneous MAB · Sub-Gaussian and sub-exponential reward settings | mean-gap independent regret upper bound: O(\sqrt{T}\ln T) | Helped |
| Use DrFed-UCB instead of GoSInE | Decentralized multi-agent MAB · Time-invariant graphs, simulation | regret AUC: 132% | Helped |
| Use DrFed-UCB instead of Gossip_UCB | Decentralized multi-agent MAB · Time-invariant graphs, simulation | regret AUC: 158% | Helped |
| Use DrFed-UCB instead of Dist_UCB | Decentralized multi-agent MAB · Time-invariant graphs, simulation | regret AUC: 128% | Helped |
| Use DrFed-UCB instead of Dist_UCB | Decentralized multi-agent MAB · Time-varying graphs, simulation | regret AUC: 96.6% | Helped |
| Use DrFed-UCB instead of Dist_UCB | Decentralized multi-agent MAB · Time-varying graphs, simulation | runtime: approximately six times faster | Helped |
| Increase reward heterogeneity | DrFed-UCB · E-R random graphs, simulation | regret | Hurt |
| Increase the number of arms | DrFed-UCB · E-R random graphs, simulation | regret | Hurt |
| Increase graph connectivity | DrFed-UCB · E-R random graphs, simulation | regret | Helped |
| Increase the number of clients | DrFed-UCB · E-R random graphs, simulation | regret | Mixed |
Closest papers by meaning
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks (NeurIPS 2025 · similarity 0.94)
- Decentralized Cooperative Stochastic Bandits (NeurIPS 2019 · similarity 0.93)
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits (NeurIPS 2025 · similarity 0.89)
- Heterogeneous Multi-Agent Bandits with Parsimonious Hints (AAAI 2025 · similarity 0.89)
- Adaptive Sample Sharing for Multi Agent Linear Bandits (ICML 2025 · similarity 0.89)
- Federated Combinatorial Multi-Agent Multi-Armed Bandits (ICML 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.