United States

Deep reinforcement learning (RL) has been applied to traffic signal control recently and demonstrated superior performance to conventional control methods. However, there are still several challenges we have to address before fully applying deep RL to traffic signal control. Firstly, the objective of traffic signal control is to optimize average travel time, which is a delayed reward in a long time horizon in the context of RL. However, existing work simplifies the optimization by using queue length, waiting time, delay, etc., as immediate reward and presumes these short-term targets are always aligned with the objective. Nevertheless, these targets may deviate from the objective in different road networks with various traffic patterns. Secondly, it remains unsolved how to cooperatively control traffic signals to directly optimize average travel time. To address these challenges, we propose a hierarchical and cooperative reinforcement learning method-HiLight. HiLight enables each agent to learn a high-level policy that optimizes the objective locally by selecting among the sub-policies that respectively optimize short-term targets. Moreover, the high-level policy additionally considers the objective in the neighborhood with adaptive weighting to encourage agents to cooperate on the objective in the road network. Empirically, we demonstrate that HiLight outperforms state-of-the-art RL methods for traffic signal control in real road networks with real traffic.

AAAI 2021

Hierarchically and Cooperatively Learning Traffic Signal Control

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS 2020

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

Barycentric spanners have been used as an efficient exploration basis in online linear optimization problems in a bandit framework. We characterise the barycentric spanner for decision problems in which the cost (or reward) is a polynomial in a single decision variable. Our characterisation of the barycentric spanner is two-fold: we show that the barycentric spanner under a polynomial cost function is the unique solution to a set of nonlinear algebraic equations, as well as the solution to a convex optimization problem. We provide numerical results to show that our method computes the barycentric spanner for the polynomial case significantly faster than the only other known algorithm for the purpose. As an application, we consider a dynamic pricing problem in which the revenue is an unknown polynomial function of the price.  We then empirically show that the use of a barycentric spanner to initialise the prior distribution in a Thompson sampling setting leads to lower cumulative regret as compared to standard initialisations. We also illustrate the importance of barycentric spanners in adversarial settings by showing, both theoretically and empirically, that a barycentric spanner achieves the minimax value in a static adversarial linear regression problem where the learner selects the training points while an adversary selects the testing points and controls the variance of the noise corrupting the training samples

Computing an Efficient Exploration Basis for Learning with Univariate Polynomial Features

In this paper, we address the large scale variation problem in crowd counting by taking full advantage of the multi-scale feature representations in a multi-level network. We implement such an idea by keeping the counting error of a patch as small as possible with a proper feature level selection strategy, since a specific feature level tends to perform better for a certain range of scales. However, without scale annotations, it is sub-optimal and error-prone to manually assign the predictions for heads of different scales to specific feature levels. Therefore, we propose a Scale-Adaptive Selection Network (SASNet), which automatically learns the internal correspondence between the scales and the feature levels. Instead of directly using the predictions from the most appropriate feature level as the final estimation, our SASNet also considers the predictions from other feature levels via weighted average, which helps to mitigate the gap between discrete feature levels and continuous scale variation. Since the heads in a local patch share roughly a same scale, we conduct the adaptive selection strategy in a patch-wise style. However, pixels within a patch contribute different counting errors due to the various difficulty degrees of learning. Thus, we further propose a Pyramid Region Awareness Loss (PRA Loss) to recursively select the most hard sub-regions within a patch until reaching the pixel level. With awareness of whether the parent patch is over-estimated or under-estimated, the fine-grained optimization with the PRA Loss for these region-aware hard pixels helps to alleviate the inconsistency problem between training target and evaluation metric. The state-of-the-art results on four datasets demonstrate the superiority of our approach.  The code will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-SASNet.

To Choose or To Fuse? Scale Selection for Crowd Counting

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some benchmarks, today's deep visual recognition pipelines tend to not generalize well in certain real-world scenarios, or for unusual viewpoints. Robotic perception, in turn, requires the capability to refine the recognition capabilities for the conditions where the mobile system operates, including cluttered indoor environments or poor illumination. This motivates the proposed task, where an agent is placed in a novel environment with the objective of improving its visual recognition capability. To study embodied visual active learning, we develop a battery of agents - both learnt and pre-specified - and with different levels of knowledge of the environment. The agents are equipped with a semantic segmentation network and seek to acquire informative views, move and explore in order to propagate annotations in the neighbourhood of those views, then refine the underlying segmentation network by online retraining. The trainable method uses deep reinforcement learning with a reward function that balances two competing objectives: task performance, represented as visual recognition accuracy, which requires exploring the environment, and the necessary amount of annotated data requested during active exploration. We extensively evaluate the proposed models using the photorealistic Matterport3D simulator and show that a fully learnt method outperforms comparable pre-specified counterparts, even when requesting fewer annotations.

Embodied Visual Active Learning for Semantic Segmentation

Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is relatively ineffective and difficult to simultaneously exploit the long-range information (e.g., the destination of the trajectory), and the short-range information (e.g., the walking direction and speed at a certain time) of the motion behavior. In this paper, we propose a temporal pyramid network for pedestrian trajectory prediction through a squeeze modulation and a dilation modulation. Our hierarchical framework builds a feature pyramid with increasingly richer temporal information from top to bottom, which can better capture the motion behavior at various tempos. Furthermore, we propose a coarse-to-fine fusion strategy with multi-supervision. By progressively merging the top coarse features of global context to the bottom fine features of rich local context, our method can fully exploit both the long-range and short-range information of the trajectory.  Experimental results on two benchmarks demonstrate the superiority of our method.  Our code and models will be available upon acceptance.

Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision

Convolutional neural networks (CNNs) have achieved remarkable results; however, despite the development of deep learning, practical user applications are fairly limited because heavy networks can be used solely with the latest hardware and software supports. Therefore, network pruning is gaining attention for general applications in various fields. This paper proposes a novel channel pruning method, Linearly Replaceable Filter (LRF), which suggests that a filter that can be approximated by the linear combination of other filters is replaceable. Moreover, an additional method called Weights Compensation is proposed to support the LRF method. This is a technique that effectively reduces the output difference caused by removing filters via direct weight modification. Through various experiments, we have confirmed that our method achieves state-of-the-art performance in several benchmarks. In particular, on ImageNet, LRF-60 reduces approximately 56% of FLOPs on ResNet-50 without top-5 accuracy drop. Further, through extensive analyses, we proved the effectiveness of our approaches.

Linearly Replaceable Filters for Deep Network Channel Pruning

Recently, a variety of regularization techniques have been widely applied in deep neural networks, which mainly focus on the regularization of weight parameters to encourage generalization effectively. Label regularization techniques are also proposed with the motivation of softening the labels while neglecting the relation of classes. Among them, the technique of knowledge distillation proposes to distill the soft label, which contains the knowledge of class relations. However, this technique needs to pre-train an extra cumbersome teacher model. In this paper, we propose a method called Knowledge Refinery (KR), which enables the neural network to learn the relation of classes on-the-fly without the teacher-student training strategy. We propose the definition of decoupled labels, which consist of the original hard label and the residual label. To exhibit the generalization of KR, we evaluate our method in both fields of computer vision and natural language processing. Our empirical results show consistent performance gains under all experimental settings.

Knowledge Refinery: Learning from Decoupled Label

Despite the prevalence of deep neural networks, their single most cited drawback is that, even when successful, their operations are inscrutable.  For many applications, the desired outputs are the composition of externally-defined bases.  For such decomposable domains, we present a two-stage learning procedure producing combinations of the external bases which are trivially extractable from the network. In the first stage, the set of external bases that will form the solution are modeled as differentiable generator modules, controlled by the same parameters as the external bases.  In the second stage, a controller network is created that selects parameters for those generators, either successively or in parallel, to compose the final solution.  Through three tasks, we concretely demonstrate how our system yields readily understandable commands.  In one, we introduce a new form of artistic style transfer, learning to draw and color with crayons, in which the transformation of a photograph or painting occurs not as a single monolithic computation, but by the composition of thousands of individual, visualizable strokes.  The other two tasks, single-pass function approximation with arbitrary bases and shape-based synthesis, show how our approach produces understandable and extractable actions in two disparate domains.

Interpretable Actions: Controlling Experts with Understandable Commands

We propose a novel recurrent neural network model, where the hidden state hâ‚œ is obtained by permuting the vector elements of the previous hidden state hâ‚œâ‚‹â‚ and adding the output of a learned function Î²(xâ‚œ) of the input xâ‚œ at time t. In our model, the prediction is given by a second learned function, which is applied to the hidden state s(hâ‚œ). The method is easy to implement, extremely efficient, and does not suffer from vanishing nor exploding gradients. In an extensive set of experiments, the method shows competitive results, in comparison to the leading literature baselines.  We share our implementation at https://github.com/rotmanmi/SRNN.

Shuffling Recurrent Neural Networks

In most machine learning tasks, we evaluate a model M on a given data population S by measuring a population-level metric F(S;M). Examples of such evaluation metric F include precision/recall for (binary) recognition, the F1 score for multi-class classification, and the BLEU metric for language generation. On the other hand, the model M is trained by optimizing a sample-level loss G(S_t; M) at each learning step t, where S_t is a subset of S (a.k.a. the mini-batch). Popular choices of G include cross-entropy loss, the Dice loss, and sentence-level BLEU scores. A fundamental assumption behind this paradigm is that the mean value of the sample-level loss G, if averaged over all possible samples, should effectively represent the population-level metric F of the task, such as, that E[ G(S_t; M) ] ~ F(S; M).  

In this paper, we systematically investigate the above assumption in several NLP tasks. We show, both theoretically and experimentally, that some popular designs of the sample-level loss G may be inconsistent with the true population-level metric F of the task, so that models trained to optimize the former can be substantially sub-optimal to the latter, a phenomenon we call it, Simpson's bias, due to its deep connections with the classic paradox known as Simpson's reversal paradox in statistics and social sciences.

Simpson's Bias in NLP Training

Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compared to autoregressive neural machine translation models due to the multimodality problem: the target words may come from multiple feasible translations. To address this problem, we propose a novel NAT framework ReorderNAT which explicitly models the reordering information to guide the decoding of NAT. Specially, ReorderNAT utilizes deterministic and non-deterministic decoding strategies that leverage reordering information as a proxy for the final translation to encourage the decoder to choose words belonging to the same translation. Experimental results on various widely-used datasets show that our proposed model achieves better performance compared to most existing NAT models, and even achieves comparable translation quality as autoregressive translation models with a significant speedup.

Downloads

Next from AAAI 2021

Computing an Efficient Exploration Basis for Learning with Univariate Polynomial Features

Similar lecture

Feudal Multi-Agent Deep Reinforcement Learning for Traffic Signal Control

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Computing an Efficient Exploration Basis for Learning with Univariate Polynomial Features

Similar lecture

Feudal Multi-Agent Deep Reinforcement Learning for Traffic Signal Control

Downloads