United States

We study the problem of episodic reinforcement learning in continuous state-action spaces with unknown rewards and transitions. Specifically, we consider the setting where the rewards and transitions are modeled using parametric bilinear exponential families. We propose an algorithm, \texttt{BEF-RLSVI}, that a) uses penalized maximum likelihood estimators to learn the unknown parameters, b) injects a calibrated Gaussian noise in the parameter of rewards to ensure exploration, and c) leverages linearity of the bilinear exponential family transitions with respect to an underlying RKHS to perform tractable planning. We further provide a frequentist regret analysis of \texttt{BEF-RLSVI} that yields an upper bound of $\tilde{\bigO}(\sqrt{d^3H^3K})$, where $d$ is the dimension of the parameters, $H$ is the episode length, and $K$ is the number of episodes. Our analysis improves the existing bounds for the bilinear exponential family of MDPs by $\sqrt{H}$ and removes the handcrafted clipping deployed in existing \texttt{RLSVI}~-type algorithms. Our regret bound is order-optimal with respect to $H$ and $K$.

AAAI 2023

Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration &amp; Planning

optimal

tractable

episodic-rl

planning

reinforcement learning

[![](https://assets.underline.io/uploads/markdown_image/1/image/21d13e03491d7e9acf6b8c46c7979c25.png)](https://docs.google.com/spreadsheets/d/1SCDDfkQk7es4J6RULKHVx1RzbB0Mutla--Sle5SVfb0/edit?usp=sharing)

**RoboCup 2021 will be Worldwide!**

We are excited to announce that RoboCup 2021 is a fully remote event with RoboCup competitions and activities taking place all over the world. Everyone is invited to participate in, or observe, the [competition leagues](https://2021.robocup.org/leagues) and the [symposium](https://2021.robocup.org/symposium)!

**RoboCup Symposium**

The 24th RoboCup International Symposium will be held in conjunction with RoboCup 2021 in a purely online setting. Scientific papers will be presented reporting innovative, original research with relevance to robotics and artificial intelligence. Within the described scope of topics we also encouraged submissions of high-quality overview articles, papers describing real-world research, and papers reporting theoretical results. In addition to the main track with regular research papers, there will be a special track focused on systems, data, and benchmarks featuring papers describing novel, open-source hardware and software systems, as well as datasets and benchmarks relevant to the community. In addition to research paper presentations, the RoboCup Symposium 2021 includes keynote talks by Dieter Fox, Jean-Paul Laumond, and Stefanie Tellex, and several interactive sessions.

**RoboCup Introduction Video**
<iframe width="995" height="516" src="https://www.youtube.com/embed/Cnh43cCsDKU" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>

Registration is required for entrance into RoboCup 2021. 
**Fees:** 
* Major Faculty or Symposium Faculty - US$50
* Major Student, Junior Mentor, Junior Student, or Symposium Student - US$20 

***Members of qualified teams:** Please contact your league for your registration password and proceed to register with your team. * 
***All non-team members:** Please register as "Symposium Only".*

You need to be registered to explore this event!

RoboCup 2021

The 24th RoboCup International Symposium will be held in conjunction with RoboCup 2021 in a purely online setting. Scientific papers will be presented reporting innovative, original research with relevance to robotics and artificial intelligence. Within the described scope of topics we also encouraged submissions of high-quality overview articles, papers describing real-world research, and papers reporting theoretical results. In addition to the main track with regular research papers, there will be a special track focused on systems, data, and benchmarks featuring papers describing novel, open-source hardware and software systems, as well as datasets and benchmarks relevant to the community. In addition to research paper presentations, the RoboCup Symposium 2021 includes keynote talks by Dieter Fox, Jean-Paul Laumond, and Stefanie Tellex, and several interactive sessions.

Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning

poster

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

Diabetic retinopathy (DR) is the main cause of irreversible blindness for working-age adults. The previous models for DR detection have difficulties in clinical application. The main reason is that most of the previous methods only use single-view data, and the single field of view (FOV) only accounts for about 13% of the FOV of the retina, resulting in the loss of most lesion features. To alleviate this problem, we propose a multi-view model for DR detection, which takes full advantage of multi-view images covering almost all of the retinal field. To be specific, we design a Cross-Interaction Self-Attention based Module (CISAM) that interfuses local features extracted from convolutional blocks with long-range global features learned from transformer blocks. Furthermore, considering the pathological association in different views, we use the feature jigsaw to assemble and learn the features of multiple views. Extensive experiments on the latest public multi-view MFIDDR dataset with 34,452 images demonstrate the superiority of our method, which performs favorably against state-of-the-art models. To the best of our knowledge, this work is the first study on the public large-scale multi-view fundus images dataset for DR detection. The code of our paper is available at github.com/XiaolingLuo/MVCINN.

MVCINN: Multi-View Diabetic Retinopathy Detection Using a Deep Cross-Interaction Neural Network

Video Grounding (VG) aims to locate the desired segment from a video given a sentence query. Recent studies have found that current VG models are prone to over-rely the groundtruth moment annotation distribution biases in the training set. To discourage the standard VG model's behavior of exploiting such temporal annotation biases and improve the model generalization ability, we propose multiple negative augmentations in a hierarchical way, including cross-video augmentations from clip-/video-level, and self-shuffled augmentations with masks. These augmentations can effectively diversify the data distribution so that the model can make more reasonable predictions instead of merely fitting the temporal biases. However, directly adopting such data augmentation strategy may inevitably carry some noise shown in our cases, since not all of the handcrafted augmentations are semantically irrelevant to the groundtruth video. To further denoise and improve the grounding accuracy, we design a multi-stage curriculum strategy to adaptively train the standard VG model from easy to hard negative augmentations. Experiments on newly collected Charades-CD and ActivityNet-CD datasets demonstrate our proposed strategy can improve the performance of the base model on both i.i.d and o.o.d scenarios.

Curriculum Multi-Negative Augmentation for Debiased Video Grounding

The generation of bimanual object manipulation sequences given a semantic action label has broad applications in collaborative robots or augmented reality. This relatively new problem differs from existing works that generate whole-body motions without any object interaction as it now requires the model to additionally learn the spatio-temporal relationship that exists between the human joints and object motion given said label. To tackle this task, we leverage the varying degree each muscle or joint is involved during object manipulation. For instance, the wrists act as the prime movers for the objects while the finger joints are angled to provide a firm grip. The remaining body joints are the least involved in that they are positioned as naturally and comfortably as possible. We thus design an architecture that comprises 3 main components: (i) a graph recurrent network that generates the wrist and object motion, (ii) an attention-based recurrent network that estimates the required finger joint angles given the graph configuration, and (iii) a recurrent network that reconstructs the body pose given the locations of the wrist. We evaluate our approach on the KIT Motion Capture and KIT RGBD Bimanual Manipulation datasets and show improvements over a simplified approach that treats the entire body as a single entity, and existing whole-body-only methods.

Action-Conditioned Generation of Bimanual Object Manipulation Sequences

Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps. 

Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition

Generalizing models trained on normal visual conditions to target domains under adverse conditions is demanding in the practical systems. One prevalent solution is to bridge the domain gap between clear- and adverse-condition images to make satisfactory prediction on the target. However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality. Furthermore, most of them mainly focus on individual adverse condition such as nighttime or foggy, weakening the model versatility when encountering other adverse weathers. To overcome the above limitations, we propose a novel framework, Visibility Boosting and Logit-Constraint learning (VBLC), tailored for superior normal-toadverse adaptation. VBLC explores the potential of getting rid of reference images and resolving the mixture of adverse conditions simultaneously. In detail, we first propose the visibility boost module to dynamically improve target images via certain priors in the image level. Then, we figure out the overconfident drawback in the conventional cross-entropy loss for self-training method and devise the logit-constraint learning, which enforces a constraint on logit outputs during training to mitigate this pain point. To the best of our knowledge, this is a new perspective for tackling such a challenging task. Extensive experiments on two normal-to-adverse domain adaptation benchmarks, i.e., Cityscapes to ACDC and Cityscapes to FoggyCityscapes + RainCityscapes, verify the effectiveness of VBLC, where it establishes the new state of the art.

VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

Low-resource relation extraction (LRE) aims to extract relations from limited labeled corpora.  Existing work takes advantages of self-training or distant supervision to expand the limited labeled data in the data-driven approaches, while the selection bias of pseudo labels may cause the error accumulation in subsequent relation classification. To address this issue, this paper proposes fmLRE, an iterative feedback method based on feature mapping similarity calculation to improve the accuracy of pseudo labels. First, it calculates the similarities between pseudo-label and real-label data of the same category in a feature mapping space based on semantic features of labeled dataset after feature projection. Then, it fine-tunes initial model according to the iterative process of reinforcement learning. Finally, the similarity is used as a threshold for screening high-precision pseudo-labels and the basis for setting different rewards, which also acts as a penalty term for the loss function of relation classifier. Experimental results demonstrate that fmLRE achieves the state-of-the-art performance compared with strong baselines on two public datasets.

fmLRE: A Low-resource Relation Extraction Model based on Feature Mapping Similarity Calculation

Unsupervised image segmentation aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS and image-wise representation learning. Based on the analysis, we argue that the existing MI-based methods in UISS suffer from representation collapse. By this, we proposed a robust network called Semantic Attention Network(SAN), in which a new module Semantic Attention(SEAT) is proposed to generate pixel-wise and semantic features dynamically. Experimental results on multiple semantic segmentation benchmarks show that our unsupervised segmentation framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods. 

Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation

Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely PHN-HVI, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.

Improving Pareto Front Learning via Multi-Sample Hypernetworks

We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call representation) and one that is task-specific (that we call predictor). The objective is to learn the optimal (representation, predictor)-pair for each task, under the assumption that the optimal representation is common to all tasks. Within this framework, efficient learning algorithms should transfer knowledge across tasks. We consider the best-arm identification problem for a fixed confidence, where, in each round, the learner actively selects both a task, and an arm, and observes the corresponding reward. We derive instance-specific sample complexity lower bounds satisfied by any $(\delta_G,\delta_H)$-PAC algorithm (such an algorithm identifies the best representation with probability at least $1-\delta_G$, and the best predictor for a task with probability at least $1-\delta_H$). We devise an algorithm \textsc{OSRL-SC} whose sample complexity approaches the lower bound, and scales at most as $H(G\log(1/\delta_G)+ X\log(1/\delta_H))$,   with $X,G,H$ being, respectively, the number of tasks, representations and predictors. By comparison, this scaling is significantly better than the classical  best-arm identification algorithm that scales as $HGX\log(1/\delta)$.

On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure

Decision diagrams for classification have some notable advantages over decision trees, as their internal connections can be determined at training time and their width is not bound to grow exponentially with their depth. Accordingly, decision diagrams are usually less prone to data fragmentation in internal nodes. However, the inherent complexity of training these classifiers acted as a long-standing barrier to their widespread adoption. In this context, we study the training of optimal decision diagrams (ODDs) from a mathematical programming perspective. We introduce a novel mixed-integer linear programming model for training and demonstrate its applicability for many datasets of practical importance. Further, we show how this model can be easily extended for fairness, parsimony, and stability notions. We present numerical analyses showing that our model allows training ODDs in short computational times, and that ODDs achieve better accuracy than optimal decision trees, while allowing for improved stability without significant accuracy losses.

Premium content

Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning

Downloads

Next from AAAI 2023

MVCINN: Multi-View Diabetic Retinopathy Detection Using a Deep Cross-Interaction Neural Network

Similar lecture

Improving Sample Efficiency in Behavior Learning by Using Sub-optimal Planners for Robots

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES