Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or bad) the decisions made by the learned agent are. Unfortunately, in a broad range of problems the design of a good reward function is not trivial, so in such cases sparse reward signals are instead adopted. The lack of a dense reward function poses new challenges, mostly related to exploration. Imitation Learning has addressed those problems by leveraging demonstrations from experts. In the absence of an expert (and its subsequent demonstrations), an option is to prioritize well-suited exploration experiences collected by the agent in order to bootstrap its learning process with good exploration behaviors. However, this solution highly depends on the ability of the agent to discover such trajectories in the early stages of its learning process. To tackle this issue, we propose to combine imitation learning with intrinsic motivation, two of the most widely adopted techniques to address problems with sparse reward. In this work intrinsic motivation is used to encourage the agent to explore the environment based on its curiosity, whereas imitation learning allows repeating the most promising experiences to accelerate the learning process. This combination is shown to yield an improved performance and better generalization in procedurally-generated environments, outperforming previously reported self-imitation learning methods and achieving equal or better sample efficiency with respect to intrinsic motivation in isolation.

深度强化学习（DRL）和深度多机构的强化学习（MARL）在包括游戏AI，自动驾驶汽车，机器人技术等各种领域取得了巨大的成功。但是，众所周知，DRL和Deep MARL代理的样本效率低下，即使对于相对简单的问题设置，通常也需要数百万个相互作用，从而阻止了在实地场景中的广泛应用和部署。背后的一个瓶颈挑战是众所周知的探索问题，即如何有效地探索环境和收集信息丰富的经验，从而使政策学习受益于最佳研究。在稀疏的奖励，吵闹的干扰，长距离和非平稳的共同学习者的复杂环境中，这个问题变得更加具有挑战性。在本文中，我们对单格和多代理RL的现有勘探方法进行了全面的调查。我们通过确定有效探索的几个关键挑战开始调查。除了上述两个主要分支外，我们还包括其他具有不同思想和技术的著名探索方法。除了算法分析外，我们还对一组常用基准的DRL进行了全面和统一的经验比较。根据我们的算法和实证研究，我们终于总结了DRL和Deep Marl中探索的公开问题，并指出了一些未来的方向。

机器学习算法中多个超参数的最佳设置是发出大多数可用数据的关键。为此目的，已经提出了几种方法，例如进化策略，随机搜索，贝叶斯优化和启发式拇指规则。在钢筋学习（RL）中，学习代理在与其环境交互时收集的数据的信息内容严重依赖于许多超参数的设置。因此，RL算法的用户必须依赖于基于搜索的优化方法，例如网格搜索或Nelder-Mead单简单算法，这对于大多数R1任务来说是非常效率的，显着减慢学习曲线和离开用户的速度有目的地偏见数据收集的负担。在这项工作中，为了使RL算法更加用户独立，提出了一种使用贝叶斯优化的自主超参数设置的新方法。来自过去剧集和不同的超参数值的数据通过执行行为克隆在元学习水平上使用，这有助于提高最大化获取功能的加强学习变体的有效性。此外，通过紧密地整合在加强学习代理设计中的贝叶斯优化，还减少了收敛到给定任务的最佳策略所需的状态转换的数量。与其他手动调整和基于优化的方法相比，计算实验显示了有希望的结果，这突出了改变算法超级参数来增加所生成数据的信息内容的好处。

任务 - 无人探索的常见方法学习塔杜拉 - RASA - 代理商假设隔离环境，没有先验的知识或经验。然而，在现实世界中，代理商在许多环境中学习，并且随着他们探索新的环境，始终伴随着事先经验。探索是一场终身的过程。在本文中，我们提出了对任务无关探索的制定和评估的范式变迁。在此设置中，代理首先学会在许多环境中探索，没有任何外在目标的任务不可行的方式。后来，代理商有效地传输了学习探索政策，以便在解决任务时更好地探索新环境。在这方面，我们评估了几种基线勘探战略，并提出了一种简单但有效的学习任务无关探索政策方法。我们的主要思想是，有两种勘探组成部分：（1）基于代理人的信仰，促进探索探索环境的经验主义部分; （2）以环境为中心的组件，鼓励探索固有的有趣物体。我们表明我们的配方是有效的，并提供多种训练测试环境对的最一致的探索。我们还介绍了评估任务无关勘探策略的基准和指标。源代码在https://github.com/sparisi/cbet/处获得。

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.

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。

We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pretrained with IL. We show that the combination of IL and RL can match human results and that good performance strongly depends on combining the allocentric information with an egocentric representation of the environment.

强化学习（RL）和脑电脑接口（BCI）是过去十年一直在增长的两个领域。直到最近，这些字段彼此独立操作。随着对循环（HITL）应用的兴趣升高，RL算法已经适用于人类指导，从而产生互动强化学习（IRL）的子领域。相邻的，BCI应用一直很感兴趣在人机交互期间从神经活动中提取内在反馈。这两个想法通过将BCI集成到IRL框架中，将RL和BCI设置在碰撞过程中，通过将内在反馈可用于帮助培训代理商来帮助框架。这种交叉点被称为内在的IRL。为了进一步帮助，促进BCI和IRL的更深层次，我们对内在IRILL的审查有着重点在于其母体领域的反馈驱动的IRL，同时还提供有关有效性，挑战和未来研究方向的讨论。

近年来，深度加固学习（DRL）已经成功地进入了复杂的决策应用，例如机器人，自动驾驶或视频游戏。违规算法往往比其策略对应物更具样本效率，并且可以从存储在重放缓冲区中存储的任何违规数据中受益。专家演示是此类数据的流行来源：代理人接触到成功的国家和行动，可以加速学习过程并提高性能。在过去，已经提出了多种想法来充分利用缓冲区中的演示，例如仅在演示或最小化额外的成本函数的预先估算。我们继续进行研究，以孤立地评估这些想法中的几个想法，以了解哪一个具有最大的影响。我们还根据给予示范和成功集中的奖励奖金，为稀疏奖励任务提供了一种新的方法。首先，我们向来自示威活动的过渡提供奖励奖金，以鼓励代理商符合所证明的行为。然后，在收集成功的剧集时，我们将其在将其添加到重播缓冲区之前与相同的奖金转换，鼓励代理也与其先前的成功相匹配。我们的实验的基本算法是流行的软演员 - 评论家（SAC），用于连续动作空间的最先进的脱核算法。我们的实验专注于操纵机器人，特别是在模拟中的机器人手臂的3D到达任务。我们表明，我们的方法Sacr2根据奖励重新标记提高了此任务的性能，即使在没有示范的情况下也是如此。

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm. Our method, which builds on top of Deep Deterministic Policy Gradients and Hindsight Experience Replay, provides an order of magnitude of speedup over RL on simulated robotics tasks. It is simple to implement and makes only the additional assumption that we can collect a small set of demonstrations. Furthermore, our method is able to solve tasks not solvable by either RL or behavior cloning alone, and often ends up outperforming the demonstrator policy.

在终生学习中，代理人在整个生命中都在不重复的一生中学习，就像人类一样，在不断变化的环境中。因此，终身学习带来了许多研究问题，例如连续领域的转移，这导致了非平稳的奖励和环境动态。由于其连续的性质，这些非平稳性很难检测和应对。因此，需要探索策略和学习方法，这些方法能够跟踪稳定的领域变化并适应它们。我们提出反应性探索，以跟踪和反应终生增强学习中持续的域转移，并相应地更新策略。为此，我们进行实验以研究不同的勘探策略。我们从经验上表明，政策阶级家族的代表更适合终身学习，因为它们比Q学习更快地适应了分销的变化。因此，政策梯度方法从反应性探索中获利最大，并在终身学习中显示出良好的结果，并进行了持续的领域变化。我们的代码可在以下网址提供：https：//github.com/ml-jku/reactive-ecploration。

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。

近年来，深度加固学习（DRL）已经成功地进入了复杂的决策应用，例如机器人，自动驾驶或视频游戏。在寻找更多采样高效的算法中，有希望的方向是利用尽可能多的外部偏离策略数据。这种数据驱动方法的一个主题是从专家演示中学习。在过去，已经提出了多种想法来利用添加到重放缓冲区的示范，例如仅在演示中预先预订或最小化额外的成本函数。我们提出了一种新的方法，能够利用任何稀疏奖励环境中在线收集的演示和剧集，以任何违规算法在线。我们的方法基于奖励奖金，给出了示范和成功的剧集，鼓励专家模仿和自模仿。首先，我们向来自示威活动的过渡提供奖励奖金，以鼓励代理商符合所证明的行为。然后，在收集成功的剧集时，我们将其在将其添加到重播缓冲区之前与相同的奖金转换，鼓励代理也与其先前的成功相匹配。我们的实验专注于操纵机器人，特别是在模拟中有6个自由的机器人手臂的三个任务。我们表明，即使在没有示范的情况下，我们基于奖励重新标记的方法可以提高基础算法（SAC和DDPG）对这些任务的性能。此外，集成到我们的方法中的两种改进来自以前的作品，允许我们的方法优于所有基线。

A long-standing challenge in artificial intelligence is lifelong learning. In lifelong learning, many tasks are presented in sequence and learners must efficiently transfer knowledge between tasks while avoiding catastrophic forgetting over long lifetimes. On these problems, policy reuse and other multi-policy reinforcement learning techniques can learn many tasks. However, they can generate many temporary or permanent policies, resulting in memory issues. Consequently, there is a need for lifetime-scalable methods that continually refine a policy library of a pre-defined size. This paper presents a first approach to lifetime-scalable policy reuse. To pre-select the number of policies, a notion of task capacity, the maximal number of tasks that a policy can accurately solve, is proposed. To evaluate lifetime policy reuse using this method, two state-of-the-art single-actor base-learners are compared: 1) a value-based reinforcement learner, Deep Q-Network (DQN) or Deep Recurrent Q-Network (DRQN); and 2) an actor-critic reinforcement learner, Proximal Policy Optimisation (PPO) with or without Long Short-Term Memory layer. By selecting the number of policies based on task capacity, D(R)QN achieves near-optimal performance with 6 policies in a 27-task MDP domain and 9 policies in an 18-task POMDP domain; with fewer policies, catastrophic forgetting and negative transfer are observed. Due to slow, monotonic improvement, PPO requires fewer policies, 1 policy for the 27-task domain and 4 policies for the 18-task domain, but it learns the tasks with lower accuracy than D(R)QN. These findings validate lifetime-scalable policy reuse and suggest using D(R)QN for larger and PPO for smaller library sizes.

Reinforcement learning (RL) algorithms have achieved notable success in recent years, but still struggle with fundamental issues in long-term credit assignment. It remains difficult to learn in situations where success is contingent upon multiple critical steps that are distant in time from each other and from a sparse reward; as is often the case in real life. Moreover, how RL algorithms assign credit in these difficult situations is typically not coded in a way that can rapidly generalize to new situations. Here, we present an approach using offline contrastive learning, which we call contrastive introspection (ConSpec), that can be added to any existing RL algorithm and addresses both issues. In ConSpec, a contrastive loss is used during offline replay to identify invariances among successful episodes. This takes advantage of the fact that it is easier to retrospectively identify the small set of steps that success is contingent upon than it is to prospectively predict reward at every step taken in the environment. ConSpec stores this knowledge in a collection of prototypes summarizing the intermediate states required for success. During training, arrival at any state that matches these prototypes generates an intrinsic reward that is added to any external rewards. As well, the reward shaping provided by ConSpec can be made to preserve the optimal policy of the underlying RL agent. The prototypes in ConSpec provide two key benefits for credit assignment: (1) They enable rapid identification of all the critical states. (2) They do so in a readily interpretable manner, enabling out of distribution generalization when sensory features are altered. In summary, ConSpec is a modular system that can be added to any existing RL algorithm to improve its long-term credit assignment.

文本冒险游戏由于其组合大的动作空间和稀疏奖励而导致加强学习方法具有独特的挑战。这两个因素的相互作用尤为苛刻，因为大型动作空间需要广泛的探索，而稀疏奖励提供有限的反馈。这项工作提出使用多级方法来解决探索 - 与利用困境，该方法明确地解除了每一集中的这两种策略。我们的算法称为Exploit-Dear-Descore（XTX），使用剥削策略开始每个剧集，该策略是从过去的一组有希望的轨迹开始，然后切换到旨在发现导致未经看不见状态空间的新动作的探索政策。该政策分解允许我们将全球决策结合在该空间中返回基于好奇的本地探索的全球决策，这是由人类可能接近这些游戏的情况。我们的方法在杰里科基准（Hausknecht等人，2020）中，在杰里科基准（Hausknecht等人，2020）中，在确定性和随机设置的比赛中显着优于27％和11％的平均正常化分数。在Zork1的游戏中，特别是，XTX获得103的得分，超过先前方法的2倍改善，并且在游戏中推过已经困扰先前的方法的游戏中的几个已知的瓶颈。

在本文中，我们通过神经生成编码的神经认知计算框架（NGC）提出了一种无反向传播的方法，以机器人控制（NGC），设计了一种完全由强大的预测性编码/处理电路构建的代理，体现计划的原则。具体而言，我们制作了一种自适应剂系统，我们称之为主动预测性编码（ACTPC），该系统可以平衡内部生成的认知信号（旨在鼓励智能探索）与内部生成的仪器信号（旨在鼓励寻求目标行为）最终学习如何使用现实的机器人模拟器（即超现实的机器人套件）来控制各种模拟机器人系统以及复杂的机器人臂，以解决块提升任务并可能选择问题。值得注意的是，我们的实验结果表明，我们提出的ACTPC代理在面对稀疏（外部）奖励信号方面表现良好，并且具有竞争力或竞争性或胜过几种强大的基于反向Prop的RL方法。

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.

强化学习代理通过鼓励最大化其总奖励的行为来学习，通常由环境提供。然而，在许多环境中，在一系列行动而不是每个单一动作之后提供奖励，导致代理在这些操作是有效的方面遇到模糊性，称为信用分配问题的问题。在本文中，我们提出了由行为心理学启发的两种策略，使代理人能够在本质上估计更多信息奖励价值，以便没有奖励。第一个策略，称为自我惩罚（SP），劝阻代理人犯错误，导致不良终端状态。第二次策略，称为奖励回填（RB），退回两个奖励行动之间的奖励。我们证明，在某些假设和不管使用的加强学习算法的情况下，这两种策略在其总奖励方面维护了所有可能政策的空间中的政策顺序，并且通过扩展，维护最佳政策。因此，我们提出的策略与任何通过经验学习价值或动作值函数的任何强化学习算法。我们将这两种策略纳入三种流行的深度加强学习方法，并在三十塔塔利游戏中评估结果。参数调整后，我们的结果表明，拟议的策略将测试方法以超过25倍的性能改善提高了超过65％的测试游戏。

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.