During training, reinforcement learning systems interact with the world without considering the safety of their actions. When deployed into the real world, such systems can be dangerous and cause harm to their surroundings. Often, dangerous situations can be mitigated by defining a set of rules that the system should not violate under any conditions. For example, in robot navigation, one safety rule would be to avoid colliding with surrounding objects and people. In this work, we define safety rules in terms of the relationships between the agent and objects and use them to prevent reinforcement learning systems from performing potentially harmful actions. We propose a new safe epsilon-greedy algorithm that uses safety rules to override agents' actions if they are considered to be unsafe. In our experiments, we show that a safe epsilon-greedy policy significantly increases the safety of the agent during training, improves the learning efficiency resulting in much faster convergence, and achieves better performance than the base model.

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.

Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learning from Demonstrations (DQfD), that leverages small sets of demonstration data to massively accelerate the learning process even from relatively small amounts of demonstration data and is able to automatically assess the necessary ratio of demonstration data while learning thanks to a prioritized replay mechanism. DQfD works by combining temporal difference updates with supervised classification of the demonstrator's actions. We show that DQfD has better initial performance than Prioritized Dueling Double Deep Q-Networks (PDD DQN) as it starts with better scores on the first million steps on 41 of 42 games and on average it takes PDD DQN 83 million steps to catch up to DQfD's performance. DQfD learns to out-perform the best demonstration given in 14 of 42 games. In addition, DQfD leverages human demonstrations to achieve state-of-the-art results for 11 games. Finally, we show that DQfD performs better than three related algorithms for incorporating demonstration data into DQN.

在过去的十年中，多智能经纪人强化学习（Marl）已经有了重大进展，但仍存在许多挑战，例如高样本复杂性和慢趋同稳定的政策，在广泛的部署之前需要克服，这是可能的。然而，在实践中，许多现实世界的环境已经部署了用于生成策略的次优或启发式方法。一个有趣的问题是如何最好地使用这些方法作为顾问，以帮助改善多代理领域的加强学习。在本文中，我们提供了一个原则的框架，用于将动作建议纳入多代理设置中的在线次优顾问。我们描述了在非传记通用随机游戏环境中提供多种智能强化代理（海军上将）的问题，并提出了两种新的基于Q学习的算法：海军上将决策（海军DM）和海军上将 - 顾问评估（Admiral-AE） ，这使我们能够通过适当地纳入顾问（Admiral-DM）的建议来改善学习，并评估顾问（Admiral-AE）的有效性。我们从理论上分析了算法，并在一般加上随机游戏中提供了关于他们学习的定点保证。此外，广泛的实验说明了这些算法：可以在各种环境中使用，具有对其他相关基线的有利相比的性能，可以扩展到大状态行动空间，并且对来自顾问的不良建议具有稳健性。

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

Efficient exploration remains a major challenge for reinforcement learning (RL). Common dithering strategies for exploration, such as -greedy, do not carry out temporally-extended (or deep) exploration; this can lead to exponentially larger data requirements. However, most algorithms for statistically efficient RL are not computationally tractable in complex environments. Randomized value functions offer a promising approach to efficient exploration with generalization, but existing algorithms are not compatible with nonlinearly parameterized value functions. As a first step towards addressing such contexts we develop bootstrapped DQN. We demonstrate that bootstrapped DQN can combine deep exploration with deep neural networks for exponentially faster learning than any dithering strategy. In the Arcade Learning Environment bootstrapped DQN substantially improves learning speed and cumulative performance across most games.

Besides the recent impressive results on reinforcement learning (RL), safety is still one of the major research challenges in RL. RL is a machine-learning approach to determine near-optimal policies in Markov decision processes (MDPs). In this paper, we consider the setting where the safety-relevant fragment of the MDP together with a temporal logic safety specification is given and many safety violations can be avoided by planning ahead a short time into the future. We propose an approach for online safety shielding of RL agents. During runtime, the shield analyses the safety of each available action. For any action, the shield computes the maximal probability to not violate the safety specification within the next $k$ steps when executing this action. Based on this probability and a given threshold, the shield decides whether to block an action from the agent. Existing offline shielding approaches compute exhaustively the safety of all state-action combinations ahead of time, resulting in huge computation times and large memory consumption. The intuition behind online shielding is to compute at runtime the set of all states that could be reached in the near future. For each of these states, the safety of all available actions is analysed and used for shielding as soon as one of the considered states is reached. Our approach is well suited for high-level planning problems where the time between decisions can be used for safety computations and it is sustainable for the agent to wait until these computations are finished. For our evaluation, we selected a 2-player version of the classical computer game SNAKE. The game represents a high-level planning problem that requires fast decisions and the multiplayer setting induces a large state space, which is computationally expensive to analyse exhaustively.

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall performance.

In this paper, we build on advances introduced by the Deep Q-Networks (DQN) approach to extend the multi-objective tabular Reinforcement Learning (RL) algorithm W-learning to large state spaces. W-learning algorithm can naturally solve the competition between multiple single policies in multi-objective environments. However, the tabular version does not scale well to environments with large state spaces. To address this issue, we replace underlying Q-tables with DQN, and propose an addition of W-Networks, as a replacement for tabular weights (W) representations. We evaluate the resulting Deep W-Networks (DWN) approach in two widely-accepted multi-objective RL benchmarks: deep sea treasure and multi-objective mountain car. We show that DWN solves the competition between multiple policies while outperforming the baseline in the form of a DQN solution. Additionally, we demonstrate that the proposed algorithm can find the Pareto front in both tested environments.

由于交通的固有复杂性和不确定性，自主驾驶决策是一项具有挑战性的任务。例如，相邻的车辆可能随时改变其车道或超越，以通过慢速车辆或帮助交通流量。预期周围车辆的意图，估算其未来状态并将其整合到自动化车辆的决策过程中，可以提高复杂驾驶场景中自动驾驶的可靠性。本文提出了一种基于预测的深入强化学习（PDRL）决策模型，该模型在公路驾驶决策过程中考虑了周围车辆的操纵意图。该模型是使用真实流量数据训练的，并通过模拟平台在各种交通条件下进行了测试。结果表明，与深入的增强学习（DRL）模型相比，提出的PDRL模型通过减少碰撞数量来改善决策绩效，从而导致更安全的驾驶。

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。

在加强学习的背景下，我们介绍了一个国家的关键性的概念，这表明在该特定状态下采取行动的选择程度影响预期的回报。也就是说，采取行动的选择更容易影响最终结果的状态被认为比它不太可能影响最终结果的国家更为重要。我们制定了基于临界的不同步骤编号算法（CVS） - 一种灵活的步骤编号算法，其利用人类提供的临界功能，或直接从环境中学到。我们在包括Atari Pong环境，道路树环境和射击环境的三个不同领域中测试它。我们展示了CVS能够优于流行的学习算法，如深Q-Learning和Monte Carlo。

基于模型的强化学习有望通过学习环境中的中间模型来预测未来的相互作用，从而从与环境的互动较少的相互作用中学习最佳政策。当预测一系列相互作用时，限制预测范围的推出长度是关键的超参数，因为预测的准确性会降低远离真实体验的区域。结果，从长远来看，从长远来看，总体上更糟糕的政策。因此，超参数提供了质量和效率之间的权衡。在这项工作中，我们将调整推出长度调整为元级的顺序决策问题的问题构成了问题，该问题优化了基于模型的强化学习所学到的最终策略，鉴于环境相互作用的固定预算通过基于反馈动态调整超参数来调整超参数。从学习过程中，例如模型的准确性和互动的其余预算。我们使用无模型的深度强化学习来解决元级决策问题，并证明我们的方法在两个众所周知的强化学习环境上优于共同的启发式基准。

本文介绍了用于交易单一资产的双重Q网络算法，即E-MINI S＆P 500连续期货合约。我们使用经过验证的设置作为我们环境的基础，并具有多个扩展。我们的贸易代理商的功能不断扩展，包括其他资产，例如商品，从而产生了四种型号。我们还应对环境条件，包括成本和危机。我们的贸易代理商首先接受了特定时间段的培训，并根据新数据进行了测试，并将其与长期策略（市场）进行了比较。我们分析了各种模型与样本中/样本外性能之间有关环境的差异。实验结果表明，贸易代理人遵循适当的行为。它可以将其政策调整为不同的情况，例如在存在交易成本时更广泛地使用中性位置。此外，净资产价值超过了基准的净值，代理商在测试集中的市场优于市场。我们使用DDQN算法对代理商在金融领域中的行为提供初步见解。这项研究的结果可用于进一步发展。

强化学习在游戏的应用中表现出了出色的表现，尤其是在Atari游戏和GO中。基于这些成功的示例，我们试图将著名的增强学习算法（深Q网络）应用于AI足球游戏。 AI足球是5：5机器人足球比赛，每个参与者都会开发一种算法，该算法控制一个团队中的五个机器人以击败对手参与者。 Deep Q-Network旨在实现我们的原始奖励，状态空间和训练每个代理的行动空间，以便在游戏过程中可以在不同情况下采取适当的操作。我们的算法能够成功地训练代理商，并且通过对10支希望参加AI足球国际比赛的10支球队的小型竞争，其表现得到了初步证明。比赛是由AI世界杯委员会组织的，并与WCG 2019 Xi'an AI大师组织。有了我们的算法，我们在这场国际比赛中与来自39个国家的130支球队的国际比赛中获得了16轮的成就。

深度加强学习（DEEPRL）方法已广泛用于机器人学，以了解环境，自主获取行为。深度互动强化学习（Deepirl）包括来自外部培训师或专家的互动反馈，提供建议，帮助学习者选择采取行动以加快学习过程。但是，目前的研究仅限于仅为特工现任提供可操作建议的互动。另外，在单个使用之后，代理丢弃该信息，该用途在为Revisit以相同状态引起重复过程。在本文中，我们提出了广泛的建议（BPA），这是一种广泛的持久的咨询方法，可以保留并重新使用加工信息。它不仅可以帮助培训师提供与类似状态相关的更一般性建议，而不是仅仅是当前状态，而且还允许代理加快学习过程。我们在两个连续机器人场景中测试提出的方法，即购物车极衡任务和模拟机器人导航任务。所得结果表明，使用BPA的代理的性能在于与深层方法相比保持培训师所需的相互作用的数量。

Learning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms. The primary difficulty arises due to insufficient exploration, resulting in an agent being unable to learn robust value functions. Intrinsically motivated agents can explore new behavior for its own sake rather than to directly solve problems. Such intrinsic behaviors could eventually help the agent solve tasks posed by the environment. We present hierarchical-DQN (h-DQN), a framework to integrate hierarchical value functions, operating at different temporal scales, with intrinsically motivated deep reinforcement learning. A top-level value function learns a policy over intrinsic goals, and a lower-level function learns a policy over atomic actions to satisfy the given goals. h-DQN allows for flexible goal specifications, such as functions over entities and relations. This provides an efficient space for exploration in complicated environments. We demonstrate the strength of our approach on two problems with very sparse, delayed feedback: (1) a complex discrete stochastic decision process, and (2) the classic ATARI game 'Montezuma's Revenge'.

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.

Safe Reinforcement Learning can be defined as the process of learning policies that maximize the expectation of the return in problems in which it is important to ensure reasonable system performance and/or respect safety constraints during the learning and/or deployment processes. We categorize and analyze two approaches of Safe Reinforcement Learning. The first is based on the modification of the optimality criterion, the classic discounted finite/infinite horizon, with a safety factor. The second is based on the modification of the exploration process through the incorporation of external knowledge or the guidance of a risk metric. We use the proposed classification to survey the existing literature, as well as suggesting future directions for Safe Reinforcement Learning.