使用规划算法和神经网络模型的基于模型的强化学习范例最近在不同的应用中实现了前所未有的结果,导致现在被称为深度增强学习的内容。这些代理非常复杂,涉及多个组件,可能会为研究产生挑战的因素。在这项工作中,我们提出了一个适用于这些类型代理的新模块化软件架构,以及一组建筑块,可以轻松重复使用和组装,以构建基于模型的增强学习代理。这些构建块包括规划算法,策略和丢失功能。我们通过将多个这些构建块组合实现和测试经过针对三种不同的测试环境的代理来说明这种架构的使用:Cartpole,Minigrid和Tictactoe。在我们的实施中提供的一个特定的规划算法,并且以前没有用于加强学习,我们称之为Imperage Minimax,在三个测试环境中取得了良好的效果。用这种架构进行的实验表明,规划算法,政策和损失函数的最佳组合依赖性严重问题。该结果提供了证据表明,拟议的架构是模块化和可重复使用的,对想要研究新环境和技术的强化学习研究人员有用。
translated by 谷歌翻译
在这项工作中,我们提出了一种初步调查一种名为DYNA-T的新算法。在钢筋学习(RL)中,规划代理有自己的环境表示作为模型。要发现与环境互动的最佳政策,代理商会收集试验和错误时尚的经验。经验可用于学习更好的模型或直接改进价值函数和政策。通常是分离的,Dyna-Q是一种混合方法,在每次迭代,利用真实体验更新模型以及值函数,同时使用模拟数据从其模型中的应用程序进行行动。然而,规划过程是计算昂贵的并且强烈取决于国家行动空间的维度。我们建议在模拟体验上构建一个上置信树(UCT),并在在线学习过程中搜索要选择的最佳动作。我们证明了我们提出的方法对来自Open AI的三个测试平台环境的一系列初步测试的有效性。与Dyna-Q相比,Dyna-T通过选择更强大的动作选择策略来优于随机环境中的最先进的RL代理。
translated by 谷歌翻译
蒙特卡洛树搜索(MCT)是设计游戏机器人或解决顺序决策问题的强大方法。该方法依赖于平衡探索和开发的智能树搜索。MCT以模拟的形式进行随机抽样,并存储动作的统计数据,以在每个随后的迭代中做出更有教育的选择。然而,该方法已成为组合游戏的最新技术,但是,在更复杂的游戏(例如那些具有较高的分支因素或实时系列的游戏)以及各种实用领域(例如,运输,日程安排或安全性)有效的MCT应用程序通常需要其与问题有关的修改或与其他技术集成。这种特定领域的修改和混合方法是本调查的主要重点。最后一项主要的MCT调查已于2012年发布。自发布以来出现的贡献特别感兴趣。
translated by 谷歌翻译
Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess and Go, where a perfect simulator is available. However, in real-world problems the dynamics governing the environment are often complex and unknown. In this work we present the MuZero algorithm which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics. MuZero learns a model that, when applied iteratively, predicts the quantities most directly relevant to planning: the reward, the action-selection policy, and the value function. When evaluated on 57 different Atari games -the canonical video game environment for testing AI techniques, in which model-based planning approaches have historically struggled -our new algorithm achieved a new state of the art. When evaluated on Go, chess and shogi, without any knowledge of the game rules, MuZero matched the superhuman performance of the AlphaZero algorithm that was supplied with the game rules.
translated by 谷歌翻译
Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarise the results from the key game and non-game domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.
translated by 谷歌翻译
In recent years, Monte Carlo tree search (MCTS) has achieved widespread adoption within the game community. Its use in conjunction with deep reinforcement learning has produced success stories in many applications. While these approaches have been implemented in various games, from simple board games to more complicated video games such as StarCraft, the use of deep neural networks requires a substantial training period. In this work, we explore on-line adaptivity in MCTS without requiring pre-training. We present MCTS-TD, an adaptive MCTS algorithm improved with temporal difference learning. We demonstrate our new approach on the game miniXCOM, a simplified version of XCOM, a popular commercial franchise consisting of several turn-based tactical games, and show how adaptivity in MCTS-TD allows for improved performances against opponents.
translated by 谷歌翻译
2048 is a single-player stochastic puzzle game. This intriguing and addictive game has been popular worldwide and has attracted researchers to develop game-playing programs. Due to its simplicity and complexity, 2048 has become an interesting and challenging platform for evaluating the effectiveness of machine learning methods. This dissertation conducts comprehensive research on reinforcement learning and computer game algorithms for 2048. First, this dissertation proposes optimistic temporal difference learning, which significantly improves the quality of learning by employing optimistic initialization to encourage exploration for 2048. Furthermore, based on this approach, a state-of-the-art program for 2048 is developed, which achieves the highest performance among all learning-based programs, namely an average score of 625377 points and a rate of 72% for reaching 32768-tiles. Second, this dissertation investigates several techniques related to 2048, including the n-tuple network ensemble learning, Monte Carlo tree search, and deep reinforcement learning. These techniques are promising for further improving the performance of the current state-of-the-art program. Finally, this dissertation discusses pedagogical applications related to 2048 by proposing course designs and summarizing the teaching experience. The proposed course designs use 2048-like games as materials for beginners to learn reinforcement learning and computer game algorithms. The courses have been successfully applied to graduate-level students and received well by student feedback.
translated by 谷歌翻译
深度强化学习(RL)导致了许多最近和开创性的进步。但是,这些进步通常以培训的基础体系结构的规模增加以及用于训练它们的RL算法的复杂性提高,而均以增加规模的成本。这些增长反过来又使研究人员更难迅速原型新想法或复制已发表的RL算法。为了解决这些问题,这项工作描述了ACME,这是一个用于构建新型RL算法的框架,这些框架是专门设计的,用于启用使用简单的模块化组件构建的代理,这些组件可以在各种执行范围内使用。尽管ACME的主要目标是为算法开发提供一个框架,但第二个目标是提供重要或最先进算法的简单参考实现。这些实现既是对我们的设计决策的验证,也是对RL研究中可重复性的重要贡献。在这项工作中,我们描述了ACME内部做出的主要设计决策,并提供了有关如何使用其组件来实施各种算法的进一步详细信息。我们的实验为许多常见和最先进的算法提供了基准,并显示了如何为更大且更复杂的环境扩展这些算法。这突出了ACME的主要优点之一,即它可用于实现大型,分布式的RL算法,这些算法可以以较大的尺度运行,同时仍保持该实现的固有可读性。这项工作提出了第二篇文章的版本,恰好与模块化的增加相吻合,对离线,模仿和从演示算法学习以及作为ACME的一部分实现的各种新代理。
translated by 谷歌翻译
游戏历史悠久的历史悠久地作为人工智能进步的基准。最近,使用搜索和学习的方法在一系列完美的信息游戏中表现出强烈的表现,并且使用游戏理论推理和学习的方法对特定的不完美信息扑克变体表示了很强的性能。我们介绍游戏玩家,一个通用算法,统一以前的方法,结合导游搜索,自助学习和游戏理论推理。游戏播放器是实现大型完美和不完美信息游戏中强大实证性能的第一个算法 - 这是一项真正的任意环境算法的重要一步。我们证明了游戏玩家是声音,融合到完美的游戏,因为可用的计算时间和近似容量增加。游戏播放器在国际象棋上达到了强大的表现,然后击败了最强大的公开可用的代理商,在头上没有限制德克萨斯州扑克(Slumbot),击败了苏格兰院子的最先进的代理人,这是一个不完美的信息游戏,说明了引导搜索,学习和游戏理论推理的价值。
translated by 谷歌翻译
传统的增强学习(RL)环境通常在培训和测试阶段都相同。因此,当前的RL方法在很大程度上不能推广到概念上相似但与已训练的方法不同的测试环境,我们将其称为新型测试环境。为了将RL研究推向可以推广到新的测试环境的算法,我们介绍了砖Tic-TAC-TOE(BTTT)测试床,其中在测试环境中的砖位与训练环境中的砖位不同。使用BTTT环境上的圆形锦标赛,我们表明传统的RL国家搜索方法,例如Monte Carlo Tree Search(MCTS)和Minimax,比Alphazero更广泛地对新型测试环境更具概括性。令人惊讶的是,Alphazero已被证明可以在GO,Chess和Shogi等环境中实现超人的性能,这可能会导致人们认为它在新颖的测试环境中的性能很好。我们的结果表明,BTTT虽然很简单,但足够丰富,可以探索Alphazero的普遍性。我们发现,仅增加MCT的lookahead迭代是不足以使Alphazero推广到一些新型的测试环境。相反,增加各种培训环境有助于逐步改善所有可能的起始砖配置中的普遍性。
translated by 谷歌翻译
This paper surveys the eld of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the eld and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but di ers considerably in the details and in the use of the word \reinforcement." The paper discusses central issues of reinforcement learning, including trading o exploration and exploitation, establishing the foundations of the eld via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.
translated by 谷歌翻译
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policybased methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep Q-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.
translated by 谷歌翻译
在这项工作中,我们提出并评估了一种新的增强学习方法,紧凑体验重放(编者),它使用基于相似转换集的复发的预测目标值的时间差异学习,以及基于两个转换的经验重放的新方法记忆。我们的目标是减少在长期累计累计奖励的经纪人培训所需的经验。它与强化学习的相关性与少量观察结果有关,即它需要实现类似于文献中的相关方法获得的结果,这通常需要数百万视频框架来培训ATARI 2600游戏。我们举报了在八个挑战街机学习环境(ALE)挑战游戏中,为仅10万帧的培训试验和大约25,000次迭代的培训试验中报告了培训试验。我们还在与基线的同一游戏中具有相同的实验协议的DQN代理呈现结果。为了验证从较少数量的观察结果近似于良好的政策,我们还将其结果与从啤酒的基准上呈现的数百万帧中获得的结果进行比较。
translated by 谷歌翻译
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges in real world deployment of autonomous driving agents. It also delineates adjacent domains such as behavior cloning, imitation learning, inverse reinforcement learning that are related but are not classical RL algorithms. The role of simulators in training agents, methods to validate, test and robustify existing solutions in RL are discussed.
translated by 谷歌翻译
有效计划的能力对于生物体和人造系统都是至关重要的。在认知神经科学和人工智能(AI)中广泛研究了基于模型的计划和假期,但是从不同的角度来看,以及难以调和的考虑(生物现实主义与可伸缩性)的不同意见(生物现实主义与可伸缩性)。在这里,我们介绍了一种新颖的方法来计划大型POMDP(Active Tree search(ACT)),该方法结合了神经科学中领先的计划理论的规范性特征和生物学现实主义(主动推论)和树木搜索方法的可扩展性AI。这种统一对两种方法都是有益的。一方面,使用树搜索可以使生物学接地的第一原理,主动推断的方法可应用于大规模问题。另一方面,主动推理为探索 - 开发困境提供了一种原则性的解决方案,该解决方案通常在树搜索方法中以启发性解决。我们的模拟表明,ACT成功地浏览了对基于抽样的方法,需要自适应探索的问题以及大型POMDP问题“ RockSample”的二进制树,其中ACT近似于最新的POMDP解决方案。此外,我们说明了如何使用ACT来模拟人类和其他解决大型计划问题的人类和其他动物的神经生理反应(例如,在海马和前额叶皮层)。这些数值分析表明,主动树搜索是神经科学和AI计划理论的原则性实现,既具有生物现实主义和可扩展性。
translated by 谷歌翻译
加固学习在机器学习中推动了令人印象深刻的进步。同时,量子增强机学习算法使用量子退火的底层划伤。最近,已经提出了一种组合两个范例的多代理强化学习(MARL)架构。这种新的算法利用Q值近似的量子Boltzmann机器(QBMS)在收敛所需的时间步长方面具有优于常规的深度增强学习。但是,该算法仅限于单代理和小型2x2多代理网格域。在这项工作中,我们提出了对原始概念的延伸,以解决更具挑战性问题。类似于Classic DQN,我们添加了重播缓冲区的体验,并使用不同的网络来估计目标和策略值。实验结果表明,学习变得更加稳定,使代理能够在具有更高复杂性的网格域中找到最佳策略。此外,我们还评估参数共享如何影响多代理域中的代理行为。量子采样证明是一种有希望的加强学习任务的方法,但目前受到QPU尺寸的限制,因此通过输入和Boltzmann机器的大小。
translated by 谷歌翻译
最近,开创性算法Alphago和Alphazero在游戏学习和深入的强化学习方面开始了一个新时代。尽管Alphago和Alphazero的成就 - 在超级人类层面上玩的GO和其他复杂游戏 - 确实令人印象深刻,但这些架构的缺点是它们需要高度的计算资源。许多研究人员正在寻找类似于alphazero但计算需求较低的方法,因此更容易重现。在本文中,我们选择了Alphazero的重要元素 - 蒙特卡洛树搜索(MCTS)计划阶段 - 并将其与时间差异(TD)学习剂相结合。我们首次将MCT包裹在TD N培训网络上,我们仅在测试时间使用此包装来创建多功能代理,从而使计算需求保持较低。我们将这种新体系结构应用于多个复杂游戏(Othello,Connectfour,Rubik的Cube),并显示了这种受alphazero启发的MCTS包装器所获得的优势。特别是,我们提出的结果是,该代理是第一个在标准硬件(无GPU或TPU)上训练的代理商,击败非常强大的Othello计划EDAX到包括7级(大多数其他学习中的学习中,从而只能失败EDAX至2级)。
translated by 谷歌翻译
Alphazero,Leela Chess Zero和Stockfish Nnue革新了计算机国际象棋。本书对此类引擎的技术内部工作进行了完整的介绍。该书分为四个主要章节 - 不包括第1章(简介)和第6章(结论):第2章引入神经网络,涵盖了所有用于构建深层网络的基本构建块,例如Alphazero使用的网络。内容包括感知器,后传播和梯度下降,分类,回归,多层感知器,矢量化技术,卷积网络,挤压网络,挤压和激发网络,完全连接的网络,批处理归一化和横向归一化和跨性线性单位,残留层,剩余层,过度效果和底漆。第3章介绍了用于国际象棋发动机以及Alphazero使用的经典搜索技术。内容包括minimax,alpha-beta搜索和蒙特卡洛树搜索。第4章展示了现代国际象棋发动机的设计。除了开创性的Alphago,Alphago Zero和Alphazero我们涵盖Leela Chess Zero,Fat Fritz,Fat Fritz 2以及有效更新的神经网络(NNUE)以及MAIA。第5章是关于实施微型α。 Shexapawn是国际象棋的简约版本,被用作为此的示例。 Minimax搜索可以解决六ap峰,并产生了监督学习的培训位置。然后,作为比较,实施了类似Alphazero的训练回路,其中通过自我游戏进行训练与强化学习结合在一起。最后,比较了类似α的培训和监督培训。
translated by 谷歌翻译
Adequately assigning credit to actions for future outcomes based on their contributions is a long-standing open challenge in Reinforcement Learning. The assumptions of the most commonly used credit assignment method are disadvantageous in tasks where the effects of decisions are not immediately evident. Furthermore, this method can only evaluate actions that have been selected by the agent, making it highly inefficient. Still, no alternative methods have been widely adopted in the field. Hindsight Credit Assignment is a promising, but still unexplored candidate, which aims to solve the problems of both long-term and counterfactual credit assignment. In this thesis, we empirically investigate Hindsight Credit Assignment to identify its main benefits, and key points to improve. Then, we apply it to factored state representations, and in particular to state representations based on the causal structure of the environment. In this setting, we propose a variant of Hindsight Credit Assignment that effectively exploits a given causal structure. We show that our modification greatly decreases the workload of Hindsight Credit Assignment, making it more efficient and enabling it to outperform the baseline credit assignment method on various tasks. This opens the way to other methods based on given or learned causal structures.
translated by 谷歌翻译
强化学习最近已成为解决棋盘游戏领域中复杂问题的非常强大的工具,其中通常需要代理来根据其自身的经验和收到的奖励来学习复杂的策略和移动。尽管RL胜过用于玩简单视频游戏和受欢迎的棋盘游戏的现有最新方法,但它尚未证明其在古代游戏中的能力。在这里,我们解决了一个这样的问题,在该问题中,我们使用不同的方法来训练代理商,即蒙特卡洛,Qlearning和Hir Hir Hight Sarsa能够学习最佳政策来发挥战略性的UR皇家游戏。我们游戏的状态空间很复杂,但是我们的代理商在玩游戏和学习重要的战略动作方面表现出令人鼓舞的结果。尽管很难得出结论,当接受有限的资源培训时,算法总体上的表现更好,但预计SARSA在学习最快的学习方面表现出了令人鼓舞的结果。
translated by 谷歌翻译