持续学习系统将知识从先前看到的任务转移以最大程度地提高新任务的能力是该领域的重大挑战，从而限制了持续学习解决方案对现实情况的适用性。因此，本研究旨在扩大我们在不断加强学习的特定情况下对转移及其驱动力的理解。我们采用SAC作为基础RL算法和持续的世界作为连续控制任务的套件。我们系统地研究SAC（演员和评论家，勘探和数据）的不同组成部分如何影响转移功效，并提供有关各种建模选项的建议。在最近的连续世界基准中评估了最佳的选择，即称为clonex-sac。 Clonex-SAC获得了87％的最终成功率，而Packnet的80％是基准中的最佳方法。此外，根据连续世界提供的指标，转移从0.18增至0.54。

我们研究了任务不合时宜的持续强化学习方法（tACRL）。 TACRL是一种结合了部分观察RL（任务不可知论的结果）和持续学习的困难（CL）的困难，即在任务的非平稳序列上学习。我们将tACRL方法与以前文献规定的软上限进行比较：多任务学习（MTL）方法，这些方法不必处理非平稳数据分布以及任务感知方法，这些方法可以在完整的情况下进行操作可观察性。我们考虑了先前未开发的基线，用于基于重播的复发性RL（3RL），其中我们增强了具有复发机制的RL算法，以减轻部分可观察性和经验经验的重播机制，以使CL中的灾难性遗忘。通过研究一系列RL任务的经验性能，我们发现3RL匹配并克服MTL和任务感知的软上限的情况令人惊讶。我们提出假设，可以解释不断的和任务不足学习研究的这个拐点。通过对流行的多任务和持续学习基准元世界的大规模研究，我们的假设在连续控制任务中进行了经验检验。通过分析包括梯度冲突在内的不同培训统计数据，我们发现证据表明3RL的表现超出其能够快速推断新任务与以前的任务的关系，从而实现前进的转移。

有效的探索是深度强化学习的关键挑战。几种方法，例如行为先验，能够利用离线数据，以便在复杂任务上有效加速加强学习。但是，如果手动的任务与所证明的任务过度偏离，则此类方法的有效性是有限的。在我们的工作中，我们建议从离线数据中学习功能，这些功能由更加多样化的任务共享，例如动作与定向之间的相关性。因此，我们介绍了无国有先验，该先验直接在显示的轨迹中直接建模时间一致性，并且即使在对简单任务收集的数据进行培训时，也能够在复杂的任务中推动探索。此外，我们通过从政策和行动之前的概率混合物中动态采样动作，引入了一种新颖的集成方案，用于非政策强化学习中的动作研究。我们将我们的方法与强大的基线相提并论，并提供了经验证据，表明它可以在稀疏奖励环境下的长途持续控制任务中加速加强学习。

We study the use of model-based reinforcement learning methods, in particular, world models for continual reinforcement learning. In continual reinforcement learning, an agent is required to solve one task and then another sequentially while retaining performance and preventing forgetting on past tasks. World models offer a task-agnostic solution: they do not require knowledge of task changes. World models are a straight-forward baseline for continual reinforcement learning for three main reasons. Firstly, forgetting in the world model is prevented by persisting existing experience replay buffers across tasks, experience from previous tasks is replayed for learning the world model. Secondly, they are sample efficient. Thirdly and finally, they offer a task-agnostic exploration strategy through the uncertainty in the trajectories generated by the world model. We show that world models are a simple and effective continual reinforcement learning baseline. We study their effectiveness on Minigrid and Minihack continual reinforcement learning benchmarks and show that it outperforms state of the art task-agnostic continual reinforcement learning methods.

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the inability to exploit previous knowledge. While considerable research has focused on learning multiple input distributions, typically in classification, lifelong reinforcement learning (LRL) must also deal with variations in the state and transition distributions, and in the reward functions. Modulating masks, recently developed for classification, are particularly suitable to deal with such a large spectrum of task variations. In this paper, we adapted modulating masks to work with deep LRL, specifically PPO and IMPALA agents. The comparison with LRL baselines in both discrete and continuous RL tasks shows competitive performance. We further investigated the use of a linear combination of previously learned masks to exploit previous knowledge when learning new tasks: not only is learning faster, the algorithm solves tasks that we could not otherwise solve from scratch due to extremely sparse rewards. The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.

The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents. Most methods devised to address this problem depend heavily on well-defined task boundaries, and thus depend on human supervision. Our task-agnostic method, Self-Activating Neural Ensembles (SANE), uses a modular architecture designed to avoid catastrophic forgetting without making any such assumptions. At the beginning of each trajectory, a module in the SANE ensemble is activated to determine the agent's next policy. During training, new modules are created as needed and only activated modules are updated to ensure that unused modules remain unchanged. This system enables our method to retain and leverage old skills, while growing and learning new ones. We demonstrate our approach on visually rich procedurally generated environments.

离线强化学习在利用大型预采用的数据集进行政策学习方面表现出了巨大的希望，使代理商可以放弃经常廉价的在线数据收集。但是，迄今为止，离线强化学习的探索相对较小，并且缺乏对剩余挑战所在的何处的了解。在本文中，我们试图建立简单的基线以在视觉域中连续控制。我们表明，对两个基于最先进的在线增强学习算法，Dreamerv2和DRQ-V2进行了简单的修改，足以超越事先工作并建立竞争性的基准。我们在现有的离线数据集中对这些算法进行了严格的评估，以及从视觉观察结果中进行离线强化学习的新测试台，更好地代表现实世界中离线增强学习问题中存在的数据分布，并开放我们的代码和数据以促进此方面的进度重要领域。最后，我们介绍并分析了来自视觉观察的离线RL所独有的几个关键Desiderata，包括视觉分散注意力和动态视觉上可识别的变化。

一种被称为优先体验重播（PER）的广泛研究的深钢筋学习（RL）技术使代理可以从与其时间差异（TD）误差成正比的过渡中学习。尽管已经表明，PER是离散作用域中深度RL方法总体性能的最关键组成部分之一，但许多经验研究表明，在连续控制中，它的表现非常低于参与者 - 批评算法。从理论上讲，我们表明，无法有效地通过具有较大TD错误的过渡对演员网络进行训练。结果，在Q网络下计算的近似策略梯度与在最佳Q功能下计算的实际梯度不同。在此激励的基础上，我们引入了一种新颖的经验重播抽样框架，用于演员批评方法，该框架还认为稳定性和最新发现的问题是Per的经验表现不佳。引入的算法提出了对演员和评论家网络的有效和高效培训的改进的新分支。一系列广泛的实验验证了我们的理论主张，并证明了引入的方法显着优于竞争方法，并获得了与标准的非政策参与者 - 批评算法相比，获得最先进的结果。

We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task. After learning a new task, the active column is distilled into the knowledge base, taking care to protect any previously acquired skills. This cycle of active learning (progression) followed by consolidation (compression) requires no architecture growth, no access to or storing of previous data or tasks, and no task-specific parameters. We demonstrate the progress & compress approach on sequential classification of handwritten alphabets as well as two reinforcement learning domains: Atari games and 3D maze navigation.

AI的一个关键挑战是构建体现的系统，该系统在动态变化的环境中运行。此类系统必须适应更改任务上下文并持续学习。虽然标准的深度学习系统实现了最先进的静态基准的结果，但它们通常在动态方案中挣扎。在这些设置中，来自多个上下文的错误信号可能会彼此干扰，最终导致称为灾难性遗忘的现象。在本文中，我们将生物学启发的架构调查为对这些问题的解决方案。具体而言，我们表明树突和局部抑制系统的生物物理特性使网络能够以特定于上下文的方式动态限制和路由信息。我们的主要贡献如下。首先，我们提出了一种新颖的人工神经网络架构，该架构将活跃的枝形和稀疏表示融入了标准的深度学习框架中。接下来，我们在需要任务的适应性的两个单独的基准上研究这种架构的性能：Meta-World，一个机器人代理必须学习同时解决各种操纵任务的多任务强化学习环境;和一个持续的学习基准，其中模型的预测任务在整个训练中都会发生变化。对两个基准的分析演示了重叠但不同和稀疏的子网的出现，允许系统流动地使用最小的遗忘。我们的神经实现标志在单一架构上第一次在多任务和持续学习设置上取得了竞争力。我们的研究揭示了神经元的生物学特性如何通知深度学习系统，以解决通常不可能对传统ANN来解决的动态情景。

设计加固学习（RL）代理通常是一个艰难的过程，需要大量的设计迭代。由于多种原因，学习可能会失败，并且标准RL方法提供的工具太少，无法洞悉确切原因。在本文中，我们展示了如何将价值分解整合到一类广泛的参与者批评算法中，并使用它来协助迭代代理设计过程。价值分解将奖励函数分为不同的组件，并学习每个组件的价值估计值。这些价值估计提供了对代理商的学习和决策过程的见解，并使新的培训方法可以减轻常见问题。作为演示，我们介绍了SAC-D，这是一种适合价值分解的软角色批评（SAC）的变体。 SAC-D保持与SAC相似的性能，同时学习一组更大的价值预测。我们还介绍了基于分解的工具来利用此信息，包括新的奖励影响指标，该指标衡量了每个奖励组件对代理决策的影响。使用这些工具，我们提供了分解用于识别和解决环境和代理设计问题的几种证明。价值分解广泛适用，易于将其纳入现有算法和工作流程中，使其成为RL从业人员的工具箱中的强大工具。

通过模仿学习（IL）使用用户提供的演示，或者通过使用大量的自主收集的体验来学习机器人技能。方法具有互补的经验和缺点：RL可以达到高度的性能，但需要缺陷，但是需要缺乏要求，但是需要达到高水平的性能，但需要达到高度的性能这可能非常耗时和不安全; IL不要求Xploration，但只学习与所提供的示范一样好的技能。一种方法将两种方法的优势结合在一起？一系列的方法旨在解决这个问题，提出了整合IL和RL的元素的各种技术。然而，扩大了这种方法，这些方法复杂的机器人技能，整合了不同的离线数据，概括到现实世界的情景仍然存在重大挑战。在本文中，USAIM是测试先前IL + RL算法的可扩展性，并设计了一种系统的详细实验实验，这些实验结合了现有的组件，其具有效果有效和可扩展的方式。为此，我们展示了一系列关于了解每个设计决定的影响的一系列实验，以便开发可以利用示范和异构的先前数据在一系列现实世界和现实的模拟问题上获得最佳表现的批准方法。我们通过致电Wap-opt的完整方法将优势加权回归[1,2]和QT-opt [3]结合在一起，提供了一个UnifiedAgveach，用于集成机器人操作的演示和离线数据。请参阅HTTPS： //awopt.github.io有关更多详细信息。

我们开发了一种新的持续元学习方法，以解决连续多任务学习中的挑战。在此设置中，代理商的目标是快速通过任何任务序列实现高奖励。先前的Meta-Creenifiltive学习算法已经表现出有希望加速收购新任务的结果。但是，他们需要在培训期间访问所有任务。除了简单地将过去的经验转移到新任务，我们的目标是设计学习学习的持续加强学习算法，使用他们以前任务的经验更快地学习新任务。我们介绍了一种新的方法，连续的元策略搜索（Comps），通过以增量方式，在序列中的每个任务上，通过序列的每个任务来消除此限制，而无需重新访问先前的任务。 Comps持续重复两个子程序：使用RL学习新任务，并使用RL的经验完全离线Meta学习，为后续任务学习做好准备。我们发现，在若干挑战性连续控制任务的旧序列上，Comps优于持续的持续学习和非政策元增强方法。

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any costly or dangerous active exploration. However, it is also challenging, due to the distributional shift between the offline training data and those states visited by the learned policy. Despite significant recent progress, the most successful prior methods are model-free and constrain the policy to the support of data, precluding generalization to unseen states. In this paper, we first observe that an existing model-based RL algorithm already produces significant gains in the offline setting compared to model-free approaches. However, standard model-based RL methods, designed for the online setting, do not provide an explicit mechanism to avoid the offline setting's distributional shift issue. Instead, we propose to modify the existing model-based RL methods by applying them with rewards artificially penalized by the uncertainty of the dynamics. We theoretically show that the algorithm maximizes a lower bound of the policy's return under the true MDP. We also characterize the trade-off between the gain and risk of leaving the support of the batch data. Our algorithm, Model-based Offline Policy Optimization (MOPO), outperforms standard model-based RL algorithms and prior state-of-the-art model-free offline RL algorithms on existing offline RL benchmarks and two challenging continuous control tasks that require generalizing from data collected for a different task. * equal contribution. † equal advising. Orders randomized.34th Conference on Neural Information Processing Systems (NeurIPS 2020),

由于其令人鼓舞的性能，在各种控制任务中的令人鼓舞的表现，深增强学习（Deep RL）一直在受到更高的关注。然而，在训练神经网络中的常规正则化技术（例如，$ L_2 $正则化，辍学）已经在RL方法中被忽略，可能是因为代理通常在相同的环境中进行培训和评估，因为Deep RL社区重点关注更多-Level算法设计。在这项工作中，我们在连续控制任务中提出了具有多种策略优化算法的正则化技术的第一综合研究。有趣的是，我们发现策略网络上的传统正则化技术通常可以带来大量改进，特别是在更难的任务上。我们的研究结果显示在训练HyperParameter变化方面是强大的。我们还将这些技术与更广泛使用的熵正则化进行了比较。此外，我们还研究正规化不同的组件，并发现策略网络通常是最佳的。我们进一步分析了为什么正则化可能有助于从四个观点来帮助推广 - 样本复杂性，奖励分配，重量规范和噪音鲁棒性。我们希望我们的研究为未来的规则策略优化算法提供指导。我们的代码可在https://github.com/xuanlinli17/ICLRR2021_RLREG上获得。

Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this work, we present CORA, a platform for Continual Reinforcement Learning Agents that provides benchmarks, baselines, and metrics in a single code package. The benchmarks we provide are designed to evaluate different aspects of the continual RL challenge, such as catastrophic forgetting, plasticity, ability to generalize, and sample-efficient learning. Three of the benchmarks utilize video game environments (Atari, Procgen, NetHack). The fourth benchmark, CHORES, consists of four different task sequences in a visually realistic home simulator, drawn from a diverse set of task and scene parameters. To compare continual RL methods on these benchmarks, we prepare three metrics in CORA: Continual Evaluation, Isolated Forgetting, and Zero-Shot Forward Transfer. Finally, CORA includes a set of performant, open-source baselines of existing algorithms for researchers to use and expand on. We release CORA and hope that the continual RL community can benefit from our contributions, to accelerate the development of new continual RL algorithms.

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.

无模型的深度增强学习（RL）已成功应用于挑战连续控制域。然而，较差的样品效率可防止这些方法广泛用于现实世界领域。我们通过提出一种新的无模型算法，现实演员 - 评论家（RAC）来解决这个问题，旨在通过学习关于Q函数的各种信任的政策家庭来解决价值低估和高估之间的权衡。我们构建不确定性惩罚Q-Learning（UPQ），该Q-Learning（UPQ）使用多个批评者的合并来控制Q函数的估计偏差，使Q函数平稳地从低于更高的置信范围偏移。随着这些批评者的指导，RAC采用通用价值函数近似器（UVFA），同时使用相同的神经网络学习许多乐观和悲观的政策。乐观的政策会产生有效的探索行为，而悲观政策会降低价值高估的风险，以确保稳定的策略更新和Q函数。该方法可以包含任何违规的演员 - 评论家RL算法。我们的方法实现了10倍的样本效率和25 \％的性能改进与SAC在最具挑战性的人形环境中，获得了11107美元的集中奖励1107美元，价格为10 ^ 6美元。所有源代码都可以在https://github.com/ihuhuhu/rac获得。

有效的探索仍然是一个重要的挑战，这可以防止为许多物理系统部署加强学习。对于具有连续和高维状态和动作空间的系统尤其如此，例如机器人操纵器。挑战在稀疏奖励环境中强调，其中设计密集奖励设计所需的低级状态信息不可用。对手仿制学习（AIL）可以通过利用专家生成的最佳行为和基本上提供替代奖励信息的替代来部分克服这一屏障。不幸的是，专家示范的可用性并不一定能够改善代理商有效探索的能力，并且正如我们经常展现所在，可以导致效率低或停滞不前。我们从引导播放（LFGP）中展示了一个框架，其中我们利用了专家演示，除了主要任务，多个辅助任务。随后，使用修改的AIL过程来使用分层模型来学习每个任务奖励和策略，其中通过组合不同任务的调度程序强制对所有任务的探索。这提供了许多好处：具有挑战瓶颈转换的主要任务的学习效率得到改善，专家数据在任务之间可重复使用，并且通过重用学习辅助任务模型的传输学习成为可能。我们在一个具有挑战性的多任务机器人操纵域中的实验结果表明我们的方法有利地对监督模仿学习和最先进的AIL方法进行比较。代码可在https://github.com/utiasstars/lfgp获得。

System identification, also known as learning forward models, transfer functions, system dynamics, etc., has a long tradition both in science and engineering in different fields. Particularly, it is a recurring theme in Reinforcement Learning research, where forward models approximate the state transition function of a Markov Decision Process by learning a mapping function from current state and action to the next state. This problem is commonly defined as a Supervised Learning problem in a direct way. This common approach faces several difficulties due to the inherent complexities of the dynamics to learn, for example, delayed effects, high non-linearity, non-stationarity, partial observability and, more important, error accumulation when using bootstrapped predictions (predictions based on past predictions), over large time horizons. Here we explore the use of Reinforcement Learning in this problem. We elaborate on why and how this problem fits naturally and sound as a Reinforcement Learning problem, and present some experimental results that demonstrate RL is a promising technique to solve these kind of problems.