We consider a general adversarial multi-armed blocking bandit setting where each played arm can be blocked (unavailable) for some time periods and the reward per arm is given at each time period adversarially without obeying any distribution. The setting models scenarios of allocating scarce limited supplies (e.g., arms) where the supplies replenish and can be reused only after certain time periods. We first show that, in the optimization setting, when the blocking durations and rewards are known in advance, finding an optimal policy (e.g., determining which arm per round) that maximises the cumulative reward is strongly NP-hard, eliminating the possibility of a fully polynomial-time approximation scheme (FPTAS) for the problem unless P = NP. To complement our result, we show that a greedy algorithm that plays the best available arm at each round provides an approximation guarantee that depends on the blocking durations and the path variance of the rewards. In the bandit setting, when the blocking durations and rewards are not known, we design two algorithms, RGA and RGA-META, for the case of bounded duration an path variation.

Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems.

On the analysis front, we establish lower bounds on the performance that is achievable by any non-anticipating policy in the presence of unknown information flows. We further show that our lower bounds can be achieved through suitable policy design.

Neural Information Processing Systems http://nips.cc/

On the analysis front, we establish lower bounds on the performance that is achievable by any non-anticipating policy in the presence of unknown information flows. We further show that our lower bounds can be achieved through suitable policy design.

While spatio-temporal Graph Neural Networks (GNNs) excel at modeling recurring traffic patterns, their reliability plummets during non-recurring events like accidents. This failure occurs because GNNs are fundamentally correlational models, learning historical patterns that are invalidated by the new causal factors introduced during disruptions. To address this, we propose Event-CausNet, a framework that uses a Large Language Model to quantify unstructured event reports, builds a causal knowledge base by estimating average treatment effects, and injects this knowledge into a dual-stream GNN-LSTM network using a novel causal attention mechanism to adjust and enhance the forecast. Experiments on a real-world dataset demonstrate that Event-CausNet achieves robust performance, reducing prediction error (MAE) by up to 35.87%, significantly outperforming state-of-the-art baselines. Our framework bridges the gap between correlational models and causal reasoning, providing a solution that is more accurate and transferable, while also offering crucial interpretability, providing a more reliable foundation for real-world traffic management during critical disruptions.

A team of reinforcement learning agents interact with the same unknown environment, share data with one another, and learn in parallel how to operate effectively.

A How General Are These Findings? A.1 The effect of outdated models persists beyond the 2018/2019 test period. Following 2.2, we derive different A.2 The effect of outdated models persists beyond the two-year gap. For this experiment, we keep the same 2018-2019 test set introduced in 2.2, and train models with We test whether the temporal degradation trend is a generalizable pattern that holds across languages. In practice, our implementation of dynamic evaluation differs from Eq. 2 in two ways: (i) We perform The x-axis presents the years in a reverse chronological order.

Running online experiments has recently become a popular approach in data-centric enterprises. However, running an experiment involves an opportunity cost or regret (e.g., exposing some users to