在大型离散图形模型中，随机规划可以简化为概率推断，但是推理的硬度需要使用近似方案。在本文中，我们认为可以沿着两个维度解开此类应用程序。第一个是理想化的精确优化目标中的信息流的方向，即向后推理。第二个是用于计算该目标解决方案的近似类型，例如，信念传播（BP）与平均场变异推理（MFVI）。这种新的分类使我们能够在先前的工作中统一大量孤立的努力，以解释其联系和差异以及潜在的改进。对大型随机计划问题进行广泛的实验评估表明，BP比基于MFVI的几种算法的优势。对MFVI的实际局限性的分析激发了一种新型算法CSVI，该算法提供了更严格的变化近似，并通过正向BP实现了可比的计划性能。

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the task, but also provide sufficient shaping to accomplish it. In this paper, we view reinforcement learning as inferring policies that achieve desired outcomes, rather than as a problem of maximizing rewards. To solve this inference problem, we establish a novel variational inference formulation that allows us to derive a well-shaped reward function which can be learned directly from environment interactions. From the corresponding variational objective, we also derive a new probabilistic Bellman backup operator and use it to develop an off-policy algorithm to solve goal-directed tasks. We empirically demonstrate that this method eliminates the need to hand-craft reward functions for a suite of diverse manipulation and locomotion tasks and leads to effective goal-directed behaviors.

主动推断是建模生物学和人造药物的行为的概率框架，该框架源于最小化自由能的原理。近年来，该框架已成功地应用于各种情况下，其目标是最大程度地提高奖励，提供可比性，有时甚至是卓越的性能与替代方法。在本文中，我们通过演示如何以及何时进行主动推理代理执行最佳奖励的动作来阐明奖励最大化和主动推断之间的联系。确切地说，我们展示了主动推理为Bellman方程提供最佳解决方案的条件 - 这种公式是基于模型的增强学习和控制的几种方法。在部分观察到的马尔可夫决策过程中，标准的主动推理方案可以为计划视野1的最佳动作产生最佳动作，但不能超越。相比之下，最近开发的递归活跃推理方案（复杂的推理）可以在任何有限的颞范围内产生最佳作用。我们通过讨论主动推理和强化学习之间更广泛的关系来补充分析。

Reinforcement learning (RL) gained considerable attention by creating decision-making agents that maximize rewards received from fully observable environments. However, many real-world problems are partially or noisily observable by nature, where agents do not receive the true and complete state of the environment. Such problems are formulated as partially observable Markov decision processes (POMDPs). Some studies applied RL to POMDPs by recalling previous decisions and observations or inferring the true state of the environment from received observations. Nevertheless, aggregating observations and decisions over time is impractical for environments with high-dimensional continuous state and action spaces. Moreover, so-called inference-based RL approaches require large number of samples to perform well since agents eschew uncertainty in the inferred state for the decision-making. Active inference is a framework that is naturally formulated in POMDPs and directs agents to select decisions by minimising expected free energy (EFE). This supplies reward-maximising (exploitative) behaviour in RL, with an information-seeking (exploratory) behaviour. Despite this exploratory behaviour of active inference, its usage is limited to discrete state and action spaces due to the computational difficulty of the EFE. We propose a unified principle for joint information-seeking and reward maximization that clarifies a theoretical connection between active inference and RL, unifies active inference and RL, and overcomes their aforementioned limitations. Our findings are supported by strong theoretical analysis. The proposed framework's superior exploration property is also validated by experimental results on partial observable tasks with high-dimensional continuous state and action spaces. Moreover, the results show that our model solves reward-free problems, making task reward design optional.

由于策略梯度定理导致的策略设置存在各种理论上 - 声音策略梯度算法，其为梯度提供了简化的形式。然而，由于存在多重目标和缺乏明确的脱助政策政策梯度定理，截止策略设置不太明确。在这项工作中，我们将这些目标统一到一个违规目标，并为此统一目标提供了政策梯度定理。推导涉及强调的权重和利息职能。我们显示多种策略来近似梯度，以识别权重（ACE）称为Actor评论家的算法。我们证明了以前（半梯度）脱离政策演员 - 评论家 - 特别是offpac和DPG - 收敛到错误的解决方案，而Ace找到最佳解决方案。我们还强调为什么这些半梯度方法仍然可以在实践中表现良好，表明ace中的方差策略。我们经验研究了两个经典控制环境的若干ACE变体和基于图像的环境，旨在说明每个梯度近似的权衡。我们发现，通过直接逼近强调权重，ACE在所有测试的所有设置中执行或优于offpac。

变异推理（VI）是一种特定类型的近似贝叶斯推断，它近似于棘手的后验分布，具有可拖动的分布。 VI将推论问题施加为优化问题，更具体地说，目标是最大程度地相对于近似后验参数，最大程度地提高边缘可能性的对数的下限。另一方面，强化学习（RL）涉及自主代理，以及如何使其最佳行动，例如最大程度地提高预期未来累积奖励的概念。在代理行动对未来环境状态没有影响的非顺序环境中，RL被上下文的土匪和贝叶斯优化涵盖。然而，在适当的顺序场景中，代理商的行为影响未来的州，即时需要对潜在的长期奖励进行仔细的奖励。该手稿显示了VI和RL的明显不同主题是如何通过两种基本方式链接的。首先，在非顺序和顺序设置中，在软策略约束下，可以通过VI目标恢复RL最大化未来累积奖励的优化目标。该政策限制不仅是人造的，而且在许多RL任务中被证明是有用的正规化程序，从而在代理性能方面得到了重大改进。其次，在基于模型的RL中，代理旨在了解其正在运行的环境，模型学习零件自然可以用作控制环境动态的过程中的推论问题。我们将区分后者的两种情况：VI时，当环境状态被代理和VI完全观察到，仅通过观察分布才能部分观察到它们。

我们介绍了一种改进政策改进的方法，该方法在基于价值的强化学习（RL）的贪婪方法与基于模型的RL的典型计划方法之间进行了插值。新方法建立在几何视野模型（GHM，也称为伽马模型）的概念上，该模型对给定策略的折现状态验证分布进行了建模。我们表明，我们可以通过仔细的基本策略GHM的仔细组成，而无需任何其他学习，可以评估任何非马尔科夫策略，以固定的概率在一组基本马尔可夫策略之间切换。然后，我们可以将广义政策改进（GPI）应用于此类非马尔科夫政策的收集，以获得新的马尔可夫政策，通常将其表现优于其先驱。我们对这种方法提供了彻底的理论分析，开发了转移和标准RL的应用，并在经验上证明了其对标准GPI的有效性，对充满挑战的深度RL连续控制任务。我们还提供了GHM培训方法的分析，证明了关于先前提出的方法的新型收敛结果，并显示了如何在深度RL设置中稳定训练这些模型。

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。

Partially observable Markov decision processes (POMDPs) provide a flexible representation for real-world decision and control problems. However, POMDPs are notoriously difficult to solve, especially when the state and observation spaces are continuous or hybrid, which is often the case for physical systems. While recent online sampling-based POMDP algorithms that plan with observation likelihood weighting have shown practical effectiveness, a general theory characterizing the approximation error of the particle filtering techniques that these algorithms use has not previously been proposed. Our main contribution is bounding the error between any POMDP and its corresponding finite sample particle belief MDP (PB-MDP) approximation. This fundamental bridge between PB-MDPs and POMDPs allows us to adapt any sampling-based MDP algorithm to a POMDP by solving the corresponding particle belief MDP, thereby extending the convergence guarantees of the MDP algorithm to the POMDP. Practically, this is implemented by using the particle filter belief transition model as the generative model for the MDP solver. While this requires access to the observation density model from the POMDP, it only increases the transition sampling complexity of the MDP solver by a factor of $\mathcal{O}(C)$, where $C$ is the number of particles. Thus, when combined with sparse sampling MDP algorithms, this approach can yield algorithms for POMDPs that have no direct theoretical dependence on the size of the state and observation spaces. In addition to our theoretical contribution, we perform five numerical experiments on benchmark POMDPs to demonstrate that a simple MDP algorithm adapted using PB-MDP approximation, Sparse-PFT, achieves performance competitive with other leading continuous observation POMDP solvers.

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.

在这项工作中，我们证明了如何通过预期最大化算法来处理随机和风险敏感的最佳控制问题。我们展示了这种处理如何实现为两个独立的迭代程序，每个迭代程序都会产生一个独特但密切相关的密度函数序列。我们激励将这些密度解释为信念，将ERGO作为确定性最佳政策的概率代理。更正式的两个固定点迭代方案是根据代表可靠的期望最大化方法的确定性最佳策略一致的固定点得出的。我们倾向于指出我们的结果与控制范式密切相关。在此推理中的控制是指旨在将最佳控制作为概率推断的实例的方法集合。尽管所说的范式已经导致了几种强大的强化学习算法的发展，但基本问题陈述通常是由目的论论证引入的。我们认为，目前的结果表明，较早的控制作为推理框架实际上将一个步骤与所提出的迭代程序中的一个步骤隔离。在任何情况下，本疗法都为他们提供了有效性的义学论点。通过暴露基本的技术机制，我们旨在为控制作为一种推断为取代当前最佳控制范式的框架的普遍接受。为了激发提出的治疗的普遍相关性，我们在勾勒出未来算法开发的大纲之前，进一步讨论了与路径积分控制和其他研究领域的相似之处。

对于许多强化学习（RL）应用程序，指定奖励是困难的。本文考虑了一个RL设置，其中代理仅通过查询可以询问可以的专家来获取有关奖励的信息，例如，评估单个状态或通过轨迹提供二进制偏好。从如此昂贵的反馈中，我们的目标是学习奖励的模型，允许标准RL算法实现高预期的回报，尽可能少的专家查询。为此，我们提出了信息定向奖励学习（IDRL），它使用奖励的贝叶斯模型，然后选择要最大化信息增益的查询，这些查询是有关合理的最佳策略之间的返回差异的差异。与针对特定类型查询设计的先前主动奖励学习方法相比，IDRL自然地适应不同的查询类型。此外，它通过将焦点转移降低奖励近似误差来实现类似或更好的性能，从而降低奖励近似误差，以改善奖励模型引起的策略。我们支持我们的调查结果，在多个环境中进行广泛的评估，并具有不同的查询类型。

This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank , that we show enables tractable learning of near-optimal behavior in these processes and is naturally small for many well-studied reinforcement learning settings. Our second contribution is a new reinforcement learning algorithm that engages in systematic exploration to learn contextual decision processes with low Bellman rank. Our algorithm provably learns near-optimal behavior with a number of samples that is polynomial in all relevant parameters but independent of the number of unique observations. The approach uses Bellman error minimization with optimistic exploration and provides new insights into efficient exploration for reinforcement learning with function approximation.

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution. We use the recently proposed amortized Stein variational gradient descent to learn a stochastic sampling network that approximates samples from this distribution. The benefits of the proposed algorithm include improved exploration and compositionality that allows transferring skills between tasks, which we confirm in simulated experiments with swimming and walking robots. We also draw a connection to actorcritic methods, which can be viewed performing approximate inference on the corresponding energy-based model.

开发了用于解决顺序实验的最佳设计的贝叶斯方法在数学上是优雅的，但在计算上具有挑战性。最近，已经提出了使用摊销的技术来使这些贝叶斯方法实用，通过培训参数化的政策，该政策在部署时有效地设计了设计。但是，这些方法可能无法充分探索设计空间，需要访问可区分的概率模型，并且只能在连续的设计空间上进行优化。在这里，我们通过证明优化政策的问题可以减少到解决马尔可夫决策过程（MDP）来解决这些局限性。我们使用现代深度强化学习技术来解决等效的MDP。我们的实验表明，即使概率模型是黑匣子，我们的方法在部署时间也很有效，并且在连续和离散的设计空间上都表现出最先进的性能。

我们考虑创建助手的问题，这些助手可以帮助代理人（通常是人类）解决新颖的顺序决策问题，假设代理人无法将奖励功能明确指定给助手。我们没有像目前的方法那样旨在自动化并代替代理人，而是赋予助手一个咨询角色，并将代理商作为主要决策者。困难是，我们必须考虑由代理商的限制或限制引起的潜在偏见，这可能导致其看似非理性地拒绝建议。为此，我们介绍了一种新颖的援助形式化，以模拟这些偏见，从而使助手推断和适应它们。然后，我们引入了一种计划助手建议的新方法，该方法可以扩展到大型决策问题。最后，我们通过实验表明我们的方法适应了这些代理偏见，并且比基于自动化的替代方案给代理带来了更高的累积奖励。

找到同一问题的不同解决方案是与创造力和对新颖情况的适应相关的智能的关键方面。在钢筋学习中，一套各种各样的政策对于勘探，转移，层次结构和鲁棒性有用。我们提出了各种各样的连续政策，一种发现在继承人功能空间中多样化的政策的方法，同时确保它们接近最佳。我们将问题形式形式化为受限制的马尔可夫决策过程（CMDP），目标是找到最大化多样性的政策，其特征在于内在的多样性奖励，同时对MDP的外在奖励保持近乎最佳。我们还分析了最近提出的稳健性和歧视奖励的绩效，并发现它们对程序的初始化敏感，并且可以收敛到次优溶液。为了缓解这一点，我们提出了新的明确多样性奖励，该奖励旨在最大限度地减少集合中策略的继承人特征之间的相关性。我们比较深度控制套件中的不同多样性机制，发现我们提出的明确多样性的类型对于发现不同的行为是重要的，例如不同的运动模式。

In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent has access to full information about the environment. We remove this assumption by developing an algorithm for IRL in partially observable Markov decision processes (POMDPs). We address two limitations of existing IRL techniques. First, they require an excessive amount of data due to the information asymmetry between the expert and the learner. Second, most of these IRL techniques require solving the computationally intractable forward problem -- computing an optimal policy given a reward function -- in POMDPs. The developed algorithm reduces the information asymmetry while increasing the data efficiency by incorporating task specifications expressed in temporal logic into IRL. Such specifications may be interpreted as side information available to the learner a priori in addition to the demonstrations. Further, the algorithm avoids a common source of algorithmic complexity by building on causal entropy as the measure of the likelihood of the demonstrations as opposed to entropy. Nevertheless, the resulting problem is nonconvex due to the so-called forward problem. We solve the intrinsic nonconvexity of the forward problem in a scalable manner through a sequential linear programming scheme that guarantees to converge to a locally optimal policy. In a series of examples, including experiments in a high-fidelity Unity simulator, we demonstrate that even with a limited amount of data and POMDPs with tens of thousands of states, our algorithm learns reward functions and policies that satisfy the task while inducing similar behavior to the expert by leveraging the provided side information.

In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important for applications where the deployment of a bad policy can be dangerous or costly. We show empirically that our algorithm produces estimates that often have orders of magnitude lower mean squared error than existing methods-it makes more efficient use of the available data. Our new estimator is based on two advances: an extension of the doubly robust estimator (Jiang & Li, 2015), and a new way to mix between model based estimates and importance sampling based estimates.

有效推论是一种数学框架，它起源于计算神经科学，作为大脑如何实现动作，感知和学习的理论。最近，已被证明是在不确定性下存在国家估算和控制问题的有希望的方法，以及一般的机器人和人工代理人的目标驱动行为的基础。在这里，我们审查了最先进的理论和对国家估计，控制，规划和学习的积极推断的实现;描述当前的成就，特别关注机器人。我们展示了相关实验，以适应，泛化和稳健性而言说明其潜力。此外，我们将这种方法与其他框架联系起来，并讨论其预期的利益和挑战：使用变分贝叶斯推理具有功能生物合理性的统一框架。