增强学习（RL）是多能管理系统的有前途的最佳控制技术。它不需要先验模型 - 降低了前期和正在进行的项目特定工程工作，并且能够学习基础系统动力学的更好表示。但是，香草RL不能提供约束满意度的保证 - 导致其在安全至关重要的环境中产生各种不安全的互动。在本文中，我们介绍了两种新颖的安全RL方法，即SafeFallback和Afvafe，其中安全约束配方与RL配方脱钩，并且提供了硬构成满意度，可以保证在培训（探索）和开发过程中（近距离） ）最佳政策。在模拟的多能系统案例研究中，我们已经表明，这两种方法均与香草RL基准相比（94,6％和82,8％，而35.5％）和香草RL基准相比明显更高的效用（即有用的政策）开始。提出的SafeFallback方法甚至可以胜过香草RL基准（102,9％至100％）。我们得出的结论是，这两种方法都是超越RL的安全限制处理技术，正如随机代理所证明的，同时仍提供坚硬的保证。最后，我们向I.A.提出了基本的未来工作。随着更多数据可用，改善约束功能本身。

多智能体增强学习（MARL）使我们能够在挑战环境中创造自适应代理，即使观察结果有限。现代Marl方法迄今为止集中于发现分解价值函数。虽然这种方法已被证明是成功的，但是由此产生的方法具有复杂的网络结构。我们采取了彻底不同的方法，并建立在独立Q-Meashers的结构上。灵感来自基于影响的抽象，我们从观察开始的观察开始，即观察动作历史的紧凑型表示可以足以学习接近最佳分散的政策。将此观察与Dueling架构，我们的算法LAN相结合，表示这些策略作为单独的个性优势功能w.r.t.一个集中的评论家。这些本地优势网络仅在单个代理的本地观察操作历史记录上。代理商表示的集中值函数条件以及环境的完整状态。在执行之前将其施加的值函数用作稳定器，该稳定器协调学习并在学习期间制定DQN目标。与其他方法相比，这使LAN能够在代理的数量中独立于其集中式网络的网络参数的数量，而不会施加像单调值函数等额外约束。在评估星际争霸多功能挑战基准测试时，LAN显示最先进的性能，并在两个以前未解决的地图`和`3S5Z_VS_3S6Z'中获得超过80％的胜利，导致QPLEL的10％的提高在14层地图上的平均性能。此外，当代理的数量变大时，LAN使用比QPlex甚至Qmix的参数明显更少。因此，我们表明LAN的结构形成了一个关键改进，有助于Marl方法保持可扩展。

我们考虑通过连续环境中的加强学习（RL）了解政策背景下的政策简化和验证的挑战。在良好的设置中，RL算法在限制中具有收敛保证。虽然这些保证是有价值的，但它们不足以安全关键型应用。此外，在应用Deep-RL等先进技术时丢失。在将先进的RL算法应用于更复杂的环境时恢复保证，（i）可达性，（ii）安全受限可达性，或（iii）折扣奖励目标，我们建立在Gelada等人介绍的深度框架上。在未知环境和学习的离散潜在模型之间获得新的双刺激界限。我们的BISIMULATION界限能够在马尔可夫决策过程中应用正式方法。最后，我们展示了如何使用通过最先进的RL获得的策略，以有效地训练变形式自动统计器，从而产生离散潜在模型，其具有可释放的近似正确的双刺激保证。此外，我们获得了潜在模型的策略的蒸馏版。

我们研究多个代理商在多目标环境的同时学习的问题。具体来说，我们考虑两种药剂重复播放一个多目标的正常形式的游戏。在这样的游戏，从联合行动所产生的收益都向量值。以基于效用的方法，我们假设效用函数存在映射向量标公用事业和考虑旨在最大限度地提高预期收益载体的效用代理。作为代理商不一定知道他们的对手的效用函数或策略，他们必须学会互动的最佳策略对方。为了帮助代理商在适当的解决办法到达，我们介绍四种新型偏好通信协议双方的合作以及自身利益的沟通。每一种方法描述了一个代理在他们的行动以及如何另一代理响应通信偏好的特定协议。这些协议是一组对不沟通基线代理5个标杆游戏随后对其进行评估。我们发现，偏好通信可以彻底改变学习的过程，并导致其没有在此设置先前观测环纳什均衡的出现。另外，还要在那里代理商必须学会当通信的通信方案。对于与纳什均衡游戏的代理，我们发现通信可以是有益的，但很难知道什么时候剂有不同的最佳平衡。如果不是这种情况，代理变得冷漠通信。在游戏没有纳什均衡，我们的结果表明，整个学习率的差异。当使用更快的学习者，我们观察到明确的沟通，在50％左右的时间变得越来越普遍，因为它可以帮助他们在学习的妥协联合政策。较慢的学生保留这种模式在较小的程度，但显示增加的冷漠。

可以将相当多的现实问题提出为决策问题，其中必须反复从一组替代方案中做出适当的选择。多次专家判断，无论是人为的还是人为的，都可以帮助做出正确的决定，尤其是在探索替代解决方案的昂贵时。由于专家意见可能会偏离，因此可以通过汇总独立判断来解决找到正确的替代方案的问题作为集体决策问题（CDM）。当前的最新方法集中于有效地找到最佳专家，因此如果所有专家均不合格或过于偏见，则表现不佳，从而可能破坏决策过程。在本文中，我们提出了一种基于上下文多臂匪徒问题（CMAB）的新算法方法，以识别和抵消这种偏见的专业知识。我们探索同质，异质和两极分化的专家小组，并表明这种方法能够有效利用集体专业知识，优于最先进的方法，尤其是当提供的专业知识质量降低时。我们的新型CMAB启发方法实现了更高的最终表现，并且在收敛的同时比以前的自适应算法更快。

Deep-learning of artificial neural networks (ANNs) is creating highly functional tools that are, unfortunately, as hard to interpret as their natural counterparts. While it is possible to identify functional modules in natural brains using technologies such as fMRI, we do not have at our disposal similarly robust methods for artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information $I_R$. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to {\em identify} computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

In recent years multi-label, multi-class video action recognition has gained significant popularity. While reasoning over temporally connected atomic actions is mundane for intelligent species, standard artificial neural networks (ANN) still struggle to classify them. In the real world, atomic actions often temporally connect to form more complex composite actions. The challenge lies in recognising composite action of varying durations while other distinct composite or atomic actions occur in the background. Drawing upon the success of relational networks, we propose methods that learn to reason over the semantic concept of objects and actions. We empirically show how ANNs benefit from pretraining, relational inductive biases and unordered set-based latent representations. In this paper we propose deep set conditioned I3D (SCI3D), a two stream relational network that employs latent representation of state and visual representation for reasoning over events and actions. They learn to reason about temporally connected actions in order to identify all of them in the video. The proposed method achieves an improvement of around 1.49% mAP in atomic action recognition and 17.57% mAP in composite action recognition, over a I3D-NL baseline, on the CATER dataset.

Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, {\textit UnitY}, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However, predicting discrete units achieves 2.51x decoding speed-up compared to that case.

Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to obtain. Self-supervised keypoint discovery is a promising strategy for estimating 3D poses without annotations. However, current keypoint discovery approaches commonly process single 2D views and do not operate in the 3D space. We propose a new method to perform self-supervised keypoint discovery in 3D from multi-view videos of behaving agents, without any keypoint or bounding box supervision in 2D or 3D. Our method uses an encoder-decoder architecture with a 3D volumetric heatmap, trained to reconstruct spatiotemporal differences across multiple views, in addition to joint length constraints on a learned 3D skeleton of the subject. In this way, we discover keypoints without requiring manual supervision in videos of humans and rats, demonstrating the potential of 3D keypoint discovery for studying behavior.

In real-world time series recognition applications, it is possible to have data with varying length patterns. However, when using artificial neural networks (ANN), it is standard practice to use fixed-sized mini-batches. To do this, time series data with varying lengths are typically normalized so that all the patterns are the same length. Normally, this is done using zero padding or truncation without much consideration. We propose a novel method of normalizing the lengths of the time series in a dataset by exploiting the dynamic matching ability of Dynamic Time Warping (DTW). In this way, the time series lengths in a dataset can be set to a fixed size while maintaining features typical to the dataset. In the experiments, all 11 datasets with varying length time series from the 2018 UCR Time Series Archive are used. We evaluate the proposed method by comparing it with 18 other length normalization methods on a Convolutional Neural Network (CNN), a Long-Short Term Memory network (LSTM), and a Bidirectional LSTM (BLSTM).