Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: \url{https://github.com/tencent-ailab/RLogist}.
translated by 谷歌翻译
The past few years have seen rapid progress in combining reinforcement learning (RL) with deep learning. Various breakthroughs ranging from games to robotics have spurred the interest in designing sophisticated RL algorithms and systems. However, the prevailing workflow in RL is to learn tabula rasa, which may incur computational inefficiency. This precludes continuous deployment of RL algorithms and potentially excludes researchers without large-scale computing resources. In many other areas of machine learning, the pretraining paradigm has shown to be effective in acquiring transferable knowledge, which can be utilized for a variety of downstream tasks. Recently, we saw a surge of interest in Pretraining for Deep RL with promising results. However, much of the research has been based on different experimental settings. Due to the nature of RL, pretraining in this field is faced with unique challenges and hence requires new design principles. In this survey, we seek to systematically review existing works in pretraining for deep reinforcement learning, provide a taxonomy of these methods, discuss each sub-field, and bring attention to open problems and future directions.
translated by 谷歌翻译
We introduce CAMRL, the first curriculum-based asymmetric multi-task learning (AMTL) algorithm for dealing with multiple reinforcement learning (RL) tasks altogether. To mitigate the negative influence of customizing the one-off training order in curriculum-based AMTL, CAMRL switches its training mode between parallel single-task RL and asymmetric multi-task RL (MTRL), according to an indicator regarding the training time, the overall performance, and the performance gap among tasks. To leverage the multi-sourced prior knowledge flexibly and to reduce negative transfer in AMTL, we customize a composite loss with multiple differentiable ranking functions and optimize the loss through alternating optimization and the Frank-Wolfe algorithm. The uncertainty-based automatic adjustment of hyper-parameters is also applied to eliminate the need of laborious hyper-parameter analysis during optimization. By optimizing the composite loss, CAMRL predicts the next training task and continuously revisits the transfer matrix and network weights. We have conducted experiments on a wide range of benchmarks in multi-task RL, covering Gym-minigrid, Meta-world, Atari video games, vision-based PyBullet tasks, and RLBench, to show the improvements of CAMRL over the corresponding single-task RL algorithm and state-of-the-art MTRL algorithms. The code is available at: https://github.com/huanghanchi/CAMRL
translated by 谷歌翻译
在合作的多代理增强学习(MARL)中,将价值​​分解与参与者 - 批评结合,使代理人能够学习随机政策,这更适合部分可观察到的环境。鉴于学习能够分散执行的本地政策的目标,通常认为代理人彼此独立,即使在集中式培训中也是如此。但是,这样的假设可能会禁止代理人学习最佳联合政策。为了解决这个问题,我们明确地将代理商之间的依赖性带入集中式培训。尽管这导致了最佳联合政策,但对于分散的执行,可能不会分解它。然而,从理论上讲,从这样的联合政策中,我们始终可以得出另一项联合政策,该政策可实现相同的最优性,但可以分解以分散的执行。为此,我们提出了多机构条件政策分解(MACPF),该政策分解(MACPF)需要进行更集中的培训,但仍可以实现分散的执行。我们在各种合作的MARL任务中验证MACPF,并证明MACPF比基线获得更好的性能或更快的收敛性。
translated by 谷歌翻译
我们研究了从连续动作空间到离散动作空间的软参与者批评(SAC)的适应性。我们重新访问香草囊,并在应用于离散设置时对其Q值低估和性能不稳定性问题提供深入的了解。因此,我们建议使用Q-CLIP的熵 - 平均Q学习和双平均Q学习来解决这些问题。对具有离散动作空间(包括Atari游戏和大型MOBA游戏)的典型基准测试的广泛实验显示了我们提出的方法的功效。我们的代码在:https://github.com/coldsummerday/revisiting-discrete-sac。
translated by 谷歌翻译
本文介绍了Kings Arena的荣誉,Kings Arena是基于国王荣誉的强化学习(RL)环境,这是世界上最受欢迎的游戏之一。与以前大多数工作中研究的其他环境相比,我们的人对竞争性强化学习提出了新的概括挑战。与对手竞争的一个代理商是一个多代理的问题;它需要概括能力,因为它具有控制和不同的对手竞争的不同目标。我们描述了国王域名荣誉的观察,动作和奖励规范,并提供了一个基于python的开源界面,以与游戏引擎进行通信。我们为纪念国王竞技场的二十个目标英雄提供了各种任务,并为具有可行的计算资源的基于RL的方法提供了初始基线结果。最后,我们展示了国王竞技场的荣誉和对挑战的可能补救措施所面临的概括挑战。所有软件(包括环境级)均可在https://github.com/tencent-ailab/hok_env上公开获得。该文档可在https://aiarena.tencent.com/hok/doc/上获得。
translated by 谷歌翻译
在动态环境中,持续增强学习(CRL)的关键挑战是,随着环境在其生命周期的变化,同时最大程度地减少对学习的信息的灾难性忘记,随着环境在其一生中的变化而变化。为了应对这一挑战,在本文中,我们提出了Dacorl,即动态自动持续RL。 Dacorl使用渐进式上下文化学习了上下文条件条件的策略,该策略会逐步将动态环境中的一系列固定任务群集成一系列上下文,并选择一个可扩展的多头神经网络以近似策略。具体来说,我们定义了一组具有类似动力学的任务,并将上下文推理形式化为在线贝叶斯无限高斯混合物集群的过程,这些过程是在环境特征上,诉诸在线贝叶斯推断,以推断上下文的后端分布。在以前的中国餐厅流程的假设下,该技术可以将当前任务准确地分类为先前看到的上下文,或者根据需要实例化新的上下文,而无需依靠任何外部指标来提前向环境变化发出信号。此外,我们采用了可扩展的多头神经网络,其输出层与新实例化的上下文同步扩展,以及一个知识蒸馏正规化项来保留学习任务的性能。作为一个可以与各种深度RL算法结合使用的一般框架,Dacorl在稳定性,整体性能和概括能力方面具有一致的优势,而不是现有方法,这是通过对几种机器人导航和Mujoco Socomotion任务进行的广泛实验来验证的。
translated by 谷歌翻译
数据爆炸和模型尺寸的增加推动了大规模机器学习的显着进步,但也使模型训练时间耗时和模型存储变得困难。为了解决具有较高计算效率和设备限制的分布式模型培训设置中的上述问题,仍然存在两个主要困难。一方面,交换信息的沟通成本,例如,不同工人之间的随机梯度是分布式培训效率的关键瓶颈。另一方面,较少的参数模型容易用于存储和通信,但是损坏模型性能的风险。为了同时平衡通信成本,模型容量和模型性能,我们提出了量化的复合镜下降自适应亚基(QCMD Adagrad),并量化正规化双平均平均自适应亚级别(QRDA ADAGRAD)进行分布式培训。具体来说,我们探讨了梯度量化和稀疏模型的组合,以降低分布式培训中每次迭代的通信成本。构建了基于量化梯度的自适应学习率矩阵,以在沟通成本,准确性和模型稀疏性之间达到平衡。此外,从理论上讲,我们发现大量化误差会引起额外的噪声,从而影响模型的收敛性和稀疏性。因此,在QCMD Adagrad和QRDA Adagrad中采用了具有相对较小误差的阈值量化策略,以提高信噪比并保留模型的稀疏性。理论分析和经验结果都证明了所提出的算法的功效和效率。
translated by 谷歌翻译
由于部分可观察性,高维视觉感知和延迟奖励,在MINECRAFT等开放世界游戏中的学习理性行为仍然是挑战,以便对加固学习(RL)研究造成挑战性,高维视觉感知和延迟奖励。为了解决这个问题,我们提出了一种具有代表学习和模仿学习的样本有效的等级RL方法,以应对感知和探索。具体来说,我们的方法包括两个层次结构,其中高级控制器学习控制策略来控制选项,低级工作人员学会解决每个子任务。为了提高子任务的学习,我们提出了一种技术组合,包括1)动作感知表示学习,其捕获了行动和表示之间的基础关系,2)基于鉴别者的自模仿学习,以实现有效的探索,以及3)合奏行为克隆一致性筛选政策鲁棒性。广泛的实验表明,Juewu-MC通过大边缘显着提高了样品效率并优于一组基线。值得注意的是,我们赢得了神经脂溢斯矿业锦标赛2021年研究竞赛的冠军,并实现了最高的绩效评分。
translated by 谷歌翻译
我们呈现协调的近端策略优化(COPPO),该算法将原始近端策略优化(PPO)扩展到多功能代理设置。关键的想法在于多个代理之间的策略更新过程中的步骤大小的协调适应。当优化理论上接地的联合目标时,我们证明了政策改进的单调性,并基于一组近似推导了简化的优化目标。然后,我们解释了Coppo中的这种目标可以在代理商之间实现动态信用分配,从而减轻了代理政策的同时更新期间的高方差问题。最后,我们证明COPPO优于几种强大的基线,并且在典型的多代理设置下,包括最新的多代理PPO方法(即MAPPO),包括合作矩阵游戏和星际争霸II微管理任务。
translated by 谷歌翻译