当应用于自动驾驶汽车设置时,行动识别可以帮助丰富环境模型对世界的理解并改善未来行动的计划。为了改善自动驾驶汽车决策,我们在这项工作中提出了一种新型的两阶段在线行动识别系统,称为RADAC。RADAC提出了主动剂检测的问题,并在直接的两阶段管道中以进行动作检测和分类的直接识别人类活动识别中的参与者关系的想法。我们表明,我们提出的计划可以胜过ICCV2021 ROAD挑战数据集上的基线,并通过将其部署在真实的车辆平台上,我们演示了对环境中代理行动的高阶理解如何可以改善对真实自动驾驶汽车的决策。
translated by 谷歌翻译
我们考虑在具有非线性函数近似的两名玩家零和马尔可夫游戏中学习NASH平衡,其中动作值函数通过繁殖内核Hilbert Space(RKHS)中的函数近似。关键挑战是如何在高维函数空间中进行探索。我们提出了一种新颖的在线学习算法,以最大程度地减少双重性差距来找到NASH平衡。我们算法的核心是基于不确定性的乐观原理得出的上和下置信度界限。我们证明,在非常温和的假设上,我们的算法能够获得$ O(\ sqrt {t})$遗憾,并在对奖励功能和马尔可夫游戏的基本动态下进行多项式计算复杂性。我们还提出了我们的算法的几个扩展,包括具有伯恩斯坦型奖励的算法,可以实现更严格的遗憾,以及用于模型错误指定的另一种算法,可以应用于神经功能近似。
translated by 谷歌翻译
由路由器控制的稀疏激活模型(MOE)层的混合物(MOE)层在深度学习方面取得了巨大的成功。但是,对这种建筑的理解仍然难以捉摸。在本文中,我们正式研究了MOE层如何改善神经网络学习的性能以及为什么混合模型不会崩溃成单个模型。我们的经验结果表明,基本问题的集群结构和专家的非线性对于MOE的成功至关重要。为了进一步理解这一点,我们考虑了固有群集结构的具有挑战性的分类问题,这很难使用单个专家学习。然而,使用MOE层,通过将专家选择为两层非线性卷积神经网络(CNN),我们表明可以成功地学习问题。此外,我们的理论表明,路由器可以学习群集中心的特征,这有助于将输入复杂问题分为单个专家可以征服的更简单的线性分类子问题。据我们所知,这是正式了解MOE层的深度学习机制的第一个结果。
translated by 谷歌翻译
汤普森采样(TS)是解决上下文多武装强盗问题最有效的算法之一。在本文中,我们提出了一种新的算法,称为神经汤普森采样,这适应了深度神经网络,用于勘探和剥削。在我们的算法的核心是一种新的奖励的后分布,其平均值是神经网络近似器,并且其方差建立在相应神经网络的神经切线特征上。我们证明,如果底层奖励函数是有界的,则可以保证所提出的算法来实现$ \ mathcal {o}(t ^ {1/2})$的累积遗憾,它与其他上下文强盗算法的遗憾匹配总轮数量$ t $。各种数据集中其他基准强盗算法的实验比较证实了我们的理论。
translated by 谷歌翻译
Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS.In this work, we analyze this problem from a novel perspective: each positive sample of one category can be seen as a negative sample for other categories, making the tail categories receive more discouraging gradients. Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories. The equalization loss protects the learning of rare categories from being at a disadvantage during the network parameter updating. Thus the model is capable of learning better discriminative features for objects of rare classes. Without any bells and whistles, our method achieves AP gains of 4.1% and 4.8% for the rare and common categories on the challenging LVIS benchmark, compared to the Mask R-CNN baseline. With the utilization of the effective equalization loss, we finally won the 1st place in the LVIS Challenge 2019. Code has been made available at: https: //github.com/tztztztztz/eql.detectron2
translated by 谷歌翻译
We study reinforcement learning (RL) with linear function approximation. For episodic time-inhomogeneous linear Markov decision processes (linear MDPs) whose transition dynamic can be parameterized as a linear function of a given feature mapping, we propose the first computationally efficient algorithm that achieves the nearly minimax optimal regret $\tilde O(d\sqrt{H^3K})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $K$ is the number of episodes. Our algorithm is based on a weighted linear regression scheme with a carefully designed weight, which depends on a new variance estimator that (1) directly estimates the variance of the \emph{optimal} value function, (2) monotonically decreases with respect to the number of episodes to ensure a better estimation accuracy, and (3) uses a rare-switching policy to update the value function estimator to control the complexity of the estimated value function class. Our work provides a complete answer to optimal RL with linear MDPs, and the developed algorithm and theoretical tools may be of independent interest.
translated by 谷歌翻译
Despite the significant interest and progress in reinforcement learning (RL) problems with adversarial corruption, current works are either confined to the linear setting or lead to an undesired $\tilde{O}(\sqrt{T}\zeta)$ regret bound, where $T$ is the number of rounds and $\zeta$ is the total amount of corruption. In this paper, we consider the contextual bandit with general function approximation and propose a computationally efficient algorithm to achieve a regret of $\tilde{O}(\sqrt{T}+\zeta)$. The proposed algorithm relies on the recently developed uncertainty-weighted least-squares regression from linear contextual bandit \citep{he2022nearly} and a new weighted estimator of uncertainty for the general function class. In contrast to the existing analysis that heavily relies on the linear structure, we develop a novel technique to control the sum of weighted uncertainty, thus establishing the final regret bounds. We then generalize our algorithm to the episodic MDP setting and first achieve an additive dependence on the corruption level $\zeta$ in the scenario of general function approximation. Notably, our algorithms achieve regret bounds either nearly match the performance lower bound or improve the existing methods for all the corruption levels and in both known and unknown $\zeta$ cases.
translated by 谷歌翻译
我们研究了协变量偏移下的线性回归,其中输入协变量的边际分布在源和目标域上有所不同,而在两个域中,给定输入协变量的输出的条件分布相似。我们根据针对此问题的目标数据(均由在线SGD进行的目标数据(均由在线SGD执行)进行预处理研究,研究了转移学习方法。我们为这种方法建立了尖锐的实例依赖性高风险上限和下限。我们的界限表明,对于大量的线性回归实例,使用$ O(n^2)$源数据(以及稀缺或无目标数据)转移学习与使用$ n $目标数据的监督学习一样有效。此外,我们表明,即使只有少量的目标数据,也可能会大大减少预处理所需的源数据量。我们的理论阐明了预处理的有效性和局限性以及对解决协变量转移问题的填补的好处。
translated by 谷歌翻译
我们研究联合的上下文线性匪徒,其中$ m $代理相互合作,在中央服务器的帮助下解决全球上下文线性匪徒问题。我们考虑了异步设置,所有代理商都独立工作,一个代理和服务器之间的通信不会触发其他代理的通信。我们提出了一种基于乐观原理的简单算法\ texttt {fedlinucb}。我们证明\ texttt {fedlinucb}的遗憾是由$ \ tilde {o}(d \ sqrt {\ sum_ {m = 1}^m t_m})$界定的,通信复杂性是$ \ tilde {o}(o}(o}(o}(o}(o))dm^2)$,其中$ d $是上下文向量的尺寸,$ t_m $是与环境的交互总数,$ m $ -th代理。据我们所知,这是第一种可证明有效的算法,它允许联合上下文线性匪徒完全异步通信,同时获得与单一代理设置相同的遗憾保证。
translated by 谷歌翻译
我们在存在对抗性腐败的情况下研究线性上下文的强盗问题,在场,每回合的奖励都被对手损坏,腐败级别(即,地平线上的腐败总数)为$ c \ geq 0 $。在这种情况下,最著名的算法受到限制,因为它们要么在计算效率低下,要么需要对腐败做出强烈的假设,或者他们的遗憾至少比没有腐败的遗憾差的$ C $倍。在本文中,为了克服这些局限性,我们提出了一种基于不确定性的乐观原则的新算法。我们算法的核心是加权山脊回归,每个选择动作的重量都取决于其置信度,直到一定的阈值。 We show that for both known $C$ and unknown $C$ cases, our algorithm with proper choice of hyperparameter achieves a regret that nearly matches the lower bounds.因此,我们的算法几乎是两种情况的对数因素的最佳选择。值得注意的是,我们的算法同时对腐败和未腐败的案件($ c = 0 $)实现了近乎最理想的遗憾。
translated by 谷歌翻译