我们确定和研究政策流失的现象，即基于价值的强化学习中贪婪政策的快速变化。政策流失以惊人的快速步伐运作，改变了少数学习更新（在Atari上的DQN等典型的深层RL设置中）中大量州的贪婪行动。我们从经验上表征了现象，验证它不限于特定算法或环境特性。许多消融有助于削弱关于为什么流失仅与深度学习有关的少数相关的合理解释。最后，我们假设政策流失是一种有益但被忽视的隐性探索形式，它以新鲜的方式铸造了$ \ epsilon $ greedy探索，即$ \ epsilon $ - noise的作用比预期的要小得多。

使用环境模型和值函数，代理可以通过向不同长度展开模型来构造状态值的许多估计，并使用其值函数引导。我们的关键识别是，人们可以将这组价值估计视为一类合奏，我们称之为\ eNPH {隐式值合奏}（IVE）。因此，这些估计之间的差异可用作代理人的认知不确定性的代理;我们将此信号术语\ EMPH {Model-Value不一致}或\ EMPH {自给智而不一致。与先前的工作不同，该工作估计通过培训许多模型和/或价值函数的集合来估计不确定性，这种方法只需要在大多数基于模型的加强学习算法中学习的单一模型和价值函数。我们在单板和函数近似设置中提供了从像素的表格和函数近似设置中的经验证据是有用的（i）作为探索的信号，（ii）在分发班次下安全地行动，（iii），用于使用基于价值的规划模型。

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.

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.

We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across states. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw pixels. We transform these pseudo-counts into exploration bonuses and obtain significantly improved exploration in a number of hard games, including the infamously difficult MONTEZUMA'S REVENGE.

In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying reinforcement learning algorithm. Our results show that this architecture leads to better policy evaluation in the presence of many similar-valued actions. Moreover, the dueling architecture enables our RL agent to outperform the state-of-the-art on the Atari 2600 domain.

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new stateof-the-art, outperforming DQN with uniform replay on 41 out of 49 games.

A Digital Twin (DT) is a simulation of a physical system that provides information to make decisions that add economic, social or commercial value. The behaviour of a physical system changes over time, a DT must therefore be continually updated with data from the physical systems to reflect its changing behaviour. For resource-constrained systems, updating a DT is non-trivial because of challenges such as on-board learning and the off-board data transfer. This paper presents a framework for updating data-driven DTs of resource-constrained systems geared towards system health monitoring. The proposed solution consists of: (1) an on-board system running a light-weight DT allowing the prioritisation and parsimonious transfer of data generated by the physical system; and (2) off-board robust updating of the DT and detection of anomalous behaviours. Two case studies are considered using a production gas turbine engine system to demonstrate the digital representation accuracy for real-world, time-varying physical systems.

Learning to predict masked tokens in a sequence has been shown to be a powerful pretraining objective for large-scale language models. After training, such masked language models can provide distributions of tokens conditioned on bidirectional context. In this short draft, we show that such bidirectional conditionals often demonstrate considerable inconsistencies, i.e., they can not be derived from a coherent joint distribution when considered together. We empirically quantify such inconsistencies in the simple scenario of bigrams for two common styles of masked language models: T5-style and BERT-style. For example, we show that T5 models often confuse its own preference regarding two similar bigrams. Such inconsistencies may represent a theoretical pitfall for the research work on sampling sequences based on the bidirectional conditionals learned by BERT-style MLMs. This phenomenon also means that T5-style MLMs capable of infilling will generate discrepant results depending on how much masking is given, which may represent a particular trust issue.

We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented with a sequence of related tasks with limited interactions per task. The agent can use its experience in each task and across tasks to estimate both the transition model and the distribution over tasks. We propose an algorithm to meta-learn the underlying structure across tasks, utilize it to plan in each task, and upper-bound the regret of the planning loss. Our bound suggests that the average regret over tasks decreases as the number of tasks increases and as the tasks are more similar. In the classical single-task setting, it is known that the planning horizon should depend on the estimated model's accuracy, that is, on the number of samples within task. We generalize this finding to meta-RL and study this dependence of planning horizons on the number of tasks. Based on our theoretical findings, we derive heuristics for selecting slowly increasing discount factors, and we validate its significance empirically.