Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms
Not on the map. Why?
Abstract (arXiv)
The problem of combinatorial multi-armed bandits with probabilistically triggered arms (CMAB-T) has been extensively studied. Prior work primarily focuses on either the online setting where an agent learns about the unknown environment through iterative interactions, or the offline setting where a policy is learned solely from logged data. However, each of these paradigms has inherent limitations: online algorithms suffer from high interaction costs and slow adaptation, while offline methods are constrained by dataset quality and lack of exploration capabilities. To address these complementary weaknesses, we propose hybrid CMAB-T, a new framework that integrates offline data with online interaction in a principled manner. Our proposed hybrid CUCB algorithm leverages offline data to guide exploration and accelerate convergence, while strategically incorporating online interactions to mitigate the insufficient coverage or distributional bias of the offline dataset. We provide theoretical guarantees on the algorithm's regret, demonstrating that hybrid CUCB significantly outperforms purely online approaches when high-quality offline data is available, and effectively corrects the bias inherent in offline-only methods when the data is limited or misaligned. Empirical results further demonstrate the consistent advantage of our algorithm.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 26 Dec 2025.
Builds on
23 of 33 references.
References · 23
- 2022Efficiently Scaling Transformer Inferencecited by 539
- 2020Is Pessimism Provably Efficient for Offline RL?cited by 364
- 2021Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimismcited by 279
- 2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 268
- 2021Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemblecited by 214
- 2022Hybrid RL: Using Both Offline and Online Data Can Make RL Efficientcited by 161
- 2024Mobile Edge Intelligence for Large Language Models: A Contemporary Surveycited by 128
- 2014Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Armscited by 79
- 2017Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applicationscited by 45
- 2023Adaptive Policy Learning for Offline-to-Online Reinforcement Learningcited by 40
- 2021Offline Neural Contextual Bandits: Pessimism, Optimization and Generalizationcited by 25
- 2022Pessimism for Offline Linear Contextual Bandits using ℓp Confidence Setscited by 18
11 more
- 2023Contextual Combinatorial Bandits with Probabilistically Triggered Armscited by 18
- 2023Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learningcited by 16
- 2022Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Armscited by 15
- 2019Online Pricing with Offline Data: Phase Transition and Inverse Square Lawcited by 13
- 2024Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Datacited by 8
- 2024Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyondcited by 7
- 2022Data-pooling Reinforcement Learning for Personalized Healthcare Interventioncited by 6
- 2024Online Bandit Learning with Offline Preference Data for Improved RLHFcited by 6
- 2025Balancing optimism and pessimism in offline-to-online learningcited by 6
- 2025Offline Learning for Combinatorial Multi-armed Banditscited by 5
- 2023Online Influence Maximization under Decreasing Cascade Modelcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.