In this paper, we propose a passivity-based methodology for analysis and design of reinforcement learning in multi-agent finite games. Starting from a known exponentiallydiscounted reinforcement learning scheme, we show that convergence to a Nash distribution can be shown in the class of games characterized by the monotonicity property of their (negative) payoff. We further exploit passivity to propose a class of higher-order schemes that preserve convergence properties, can improve the speed of convergence and can even converge in cases whereby their first-order counterpart fail to converge. We demonstrate these properties through numerical simulations for several representative games. arXiv:1808.04464v1 [math.OC]

No abstract

No abstract

Small-scale pedestrian detection and occluded pedestrian detection are two challenging tasks. However, most state-of-the-art methods merely handle one single task each time, thus giving rise to relatively poor performance when the two tasks, in practise, are required simultaneously. In this paper, it is found that small-scale pedestrian detection and occluded pedestrian detection actually have a common problem, i.e., inaccurate location problem. Therefore, solving this problem enables to improve the performance of both tasks. To this end, we pay more attention to the predicted bounding box with worse location precision and extract more contextual information around objects, where two modules (i.e., location bootstrap and semantic transition) are respectively proposed. The location bootstrap is used to re-weight the regression loss, where the loss of predicted bounding box far from the corresponding groundtruth is up-weighted and the loss of predicted bounding box near the corresponding ground-truth is down-weighted. Meanwhile, the semantic transition adds more contextual information and relieves the semantic inconsistency of skip-layer fusion. Since the location bootstrap is not used at the test stage and the semantic transition is light-weight, the proposed method does not add much extra computational costs during inference. Experiments on the challenging Citypersons and Caltech datasets show that the proposed method outperforms the state-of-the-art methods on the small-scale pedestrians and occluded pedestrians (e.g., 5.20% and 4.73% improvements on the Caltech).Index Terms-Small-scale pedestrians, occluded pedestrians, location bootstrap, and semantic transition. J. Cao and Y. Pang are with the

No abstract