Canada

Safe Reinforcement Learning (SRL) algorithms aim to learn a policy that maximizes the reward while satisfying the safety constraints. One of the challenges in SRL is that it is often difficult to balance the two objectives of reward maximization and safety constraint satisfaction. Existing algorithms utilize constraint optimization techniques like penalty-based, barrier penalty-based, and Lagrangian-based dual or primal policy optimizations methods. However, they suffer from training oscillations and approximation errors, which impact the overall learning objectives.

This paper proposes the Permeable Penalty Barrier-based Policy Optimization (P2BPO) algorithm that addresses this issue by allowing a small fraction of penalty beyond the penalty barrier, and a parameter is used to control this permeability. In addition, an adaptive penalty parameter is used instead of a constant one, which is initialized with a low value and increased gradually as the agent violates the safety constraints. We have also provided a theoretical proof of the proposed method&#39;s performance guarantee bound, which ensures that P2BPO can learn a policy satisfying the safety constraints with high probability while achieving a higher expected reward. Furthermore, we compare P2BPO with other SRL algorithms on various SRL tasks and demonstrate that it achieves better rewards while adhering to the constraints.

AAAI 2024

P2BPO: Permeable Penalty Barrier-Based Policy Optimization for Safe RL

reinforcement learning theory

reinforcement learning algorithms

optimization

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. 

AAAI 2022

Safe Reinforcement Learning (SRL) algorithms aim to learn a policy that maximizes the reward while satisfying the safety constraints. One of the challenges in SRL is that it is often difficult to balance the two objectives of reward maximization and safety constraint satisfaction. Existing algorithms utilize constraint optimization techniques like penalty-based, barrier penalty-based, and Lagrangian-based dual or primal policy optimizations methods. However, they suffer from training oscillations and approximation errors, which impact the overall learning objectives.

This paper proposes the Permeable Penalty Barrier-based Policy Optimization (P2BPO) algorithm that addresses this issue by allowing a small fraction of penalty beyond the penalty barrier, and a parameter is used to control this permeability. In addition, an adaptive penalty parameter is used instead of a constant one, which is initialized with a low value and increased gradually as the agent violates the safety constraints. We have also provided a theoretical proof of the proposed method's performance guarantee bound, which ensures that P2BPO can learn a policy satisfying the safety constraints with high probability while achieving a higher expected reward. Furthermore, we compare P2BPO with other SRL algorithms on various SRL tasks and demonstrate that it achieves better rewards while adhering to the constraints.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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. 

The selection of the assumed effect size (AES) critically determines the duration of an experiment, and hence its accuracy and efficiency. Traditionally, experimenters determine AES based on domain knowledge. However, this method becomes impractical for online experimentation services managing numerous experiments, and  a more automated approach is hence of great  demand. We initiate the study of data-driven AES selection in for online experimentation services by introducing two  solutions. The first employs a three-layer Gaussian Mixture Model considering the heteroskedasticity across experiments, and it seeks to estimate the true expected effect size among  positive experiments. The second method, grounded in utility theory, aims to determine the optimal effect size by striking a balance between the experiment's cost and the precision of decision-making. Through comparisons with baseline methods using both simulated and real data, we showcase the superior performance of the proposed approaches.

Effect Size Estimation for Duration Recommendation in Online Experiments: Leveraging Hierarchical Models and Objective Utility Approaches | VIDEO

This work tackles the important task of understanding out-of-distribution behavior in two prominent types of generative models, i.e., GANs and Diffusion models. Understanding this behavior is crucial in understanding their broader utility and risks as these systems are increasingly deployed in our daily lives. Our first contribution is demonstrating that diffusion spaces outperform GANs' latent spaces in inverting high-quality OOD images. We also provide a theoretical analysis attributing this to the lack of prior holes in diffusion spaces. Our second significant contribution is to provide a theoretical hypothesis that diffusion spaces can be projected onto a bounded hypersphere, enabling image manipulation through geodesic traversal between inverted images. Our analysis shows that different geodesics share common attributes for the same manipulation, which we leverage to perform various image manipulations. We conduct thorough empirical evaluations to support and validate our claims. Finally, our third and final contribution introduces a novel approach to the few-shot sampling for out-of-distribution data by inverting a few images to sample from the cluster formed by the inverted latents. The proposed technique achieves state-of-the-art results for the few-shot generation task in terms of image quality. The effectiveness of the generated samples is further validated when used to augment data for underrepresented classes in a classification task, leading to improved performance. Our research underscores the promise of diffusion spaces in out-of-distribution imaging and offers avenues for further exploration.

Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data

Numerous methods are proposed for the Traffic Signal Control (TSC) tasks aiming to provide efficient transportation and mitigate congestion waste. In recent, promising results have been attained by Reinforcement Learning (RL) methods through trial and error in simulators, bringing confidence in solving cities' congestion headaches. However, there still exist performance gaps when simulator-trained policies are deployed to the real world. This issue is mainly introduced by the system dynamic difference between the training simulator and the real-world environments. The Large Language Models (LLMs) are trained on mass knowledge and proved to be equipped with astonishing inference abilities.
In this work, we leverage LLMs to understand and profile the system dynamics by a prompt-based grounded action transformation. Accepting the cloze prompt template, then filling in the answer based on accessible context, the pre-trained LLM's inference ability is exploited and applied to understand how weather conditions, traffic states, and road types influence traffic dynamics, being aware of this, the policies' action is taken and grounded based on realistic dynamics, thus help the agent learn a more realistic policy. We conduct experiments using DQN to show the effectiveness of the proposed PromptGAT's ability in mitigating the performance gap from simulation to reality (sim-to-real).

Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning

Removing shadows requires an understanding of both lighting conditions and object textures in a scene. Existing methods typically learn pixel-level color mappings between
shadow and non-shadow images, in which the joint modeling of lighting and object textures is implicit and inadequate. We observe that in a shadow region, the degradation degree of object textures depends on the local illumination, while simply enhancing the local illumination cannot fully recover the attenuated textures. Based on this observation, we propose to condition the restoration of attenuated textures on the corrected local lighting in the shadow region. Specifically, We first design a shadow-aware decomposition network to estimate the illumination and reflectance layers of shadow regions explicitly. We then propose a novel bilateral correction network to recast the lighting of shadow regions in the illumination layer via a novel local lighting correction module, and to restore the textures conditioned on the corrected illumination layer via a novel illumination-guided texture restoration module. We further annotate pixel-wise shadow masks for the public SRD dataset, which originally contains only image pairs. Experiments on three benchmarks show that our method outperforms existing state-of-the-art shadow removal methods.  Project page in: yuhaoliu7456.github.io/RRL-Net.

Recasting Regional Lighting for Shadow Removal

Artificial Intelligence (AI) models have become an integral part of modern society, significantly improving human lives. However, ensuring the reliability and safety of these models is of paramount importance. One critical aspect is the continuous monitoring and verification of model performance to prevent any potential risks. Real-time online evaluation of AI models is necessary to maintain their effectiveness and mitigate any harm caused by performance degradation. The traditional approach to model evaluation involves supervised methods that rely on manual labeling to compare results with model predictions. Unfortunately, this method is not suitable for online model monitoring due to its inherent lag and high cost. While there have been attempts to explore free-label model evaluation, these approaches often consider only the global features of the entire dataset. Additionally, they can only perform model evaluation based on a single dimension of model confidence or features. In this paper, we propose a novel approach called Divide-and-Aggregate Learning (DAL) for unsupervised model evaluation. Our method addresses the limitations of previous approaches by dividing the output of the model into buckets, capturing local information of the distribution. We then aggregate this local information to obtain global information and further represent the relationship between the distribution and model performance. Importantly, our method can simultaneously handle the confidence distribution and feature distribution of the model output. Extensive experiments have been conducted to demonstrate the effectiveness of our DAL model. The results show that our approach outperforms previous methods on four widely used datasets. We will make our source code publicly available.

Divide-and-Aggregate Learning for Evaluating Performance on Unlabeled Data

Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, generally leading to overestimation of methods' real-world utility.  In this work, we seek to address this by conducting a study that evaluates post-hoc explainable ML methods in a setting consistent with the application context and provide a template for future evaluation studies. We modify and improve a prior study on e-commerce fraud detection by relaxing the original work's simplifying assumptions that departed from the deployment context. Our study finds no evidence for the utility of the tested explainable ML methods in the context, which is a drastically different conclusion from the earlier work. This highlights how seemingly trivial experimental design choices can yield misleading conclusions about method utility. In addition, our work carries lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended application context but also developing methods tailored to specific applications, moving beyond general-purpose explainable ML methods.

On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods

Dear Chairs,
I am writing to express my strong interest in the AAAI
2024 New Faculty Highlights opportunity. Currently serving
as an Assistant Professor at the University of Texas at Dal-
las since August 2022, I am working on computer vision and
machine learning. My research focuses are transfer learning,
continual learning, multi-task learning, and geometric learn-
ing. I have published more than 30 papers with a total cita-
tions over 1300 (https://scholar.google.com/citations?user=
BxIXuZYAAAAJ&hl=en). Most of them are at top confer-
ences such as CVPR, ECCV, ICCV, NeurIPS, and AAAI.
In the following sections, I will provide an overview of my
research accomplishments to date and outline my future re-
search plans.

Application for New Faculty Highlights

"This Model Assignment consists of two “sister” lab exercises related to counting LEGO pieces using computer vision techniques.

In the first lab, students are tasked with using traditional computer vision techniques to count and classify LEGO pieces from a small image dataset. All images feature several LEGO pieces against a relatively simple background. Students need to apply three techniques such as image thresholding, edge detection (e.g., Canny), and rg chromaticity to segment, count and classify the pieces (by color). Students are expected to identify the most suitable technique and provide evidence to support their choice. They should also provide a report containing method descriptions, results, discussion, and conclusion.

For the second lab, students work with a larger and more complex dataset to detect and count LEGO pieces. Students need to train a convolutional neural network to identify and count LEGO pieces. They can choose any neural network architecture and framework (e.g., Inception/SSD with TensorFlow, Mask R-CNN with PyTorch, YOLO with Darknet). The performance assessment for the object detection task involves using mean average precision (mAP) with an IoU threshold of 0.5. The assignment requires a similar report structure as the first lab."

Using Computer Vision Techniques to Count LEGO Pieces

For more than 15 years, my team and I have been focused on AI for social impact, deploying end-to-end systems in areas of public health, conservation and public safety. In this talk, I will highlight the results from our deployments for social impact in public health and conservation, as well as required innovations in integrating machine learning and optimization. Within public health, I will present recent results from our work in India with the world’s two largest mobile health programs for maternal and child care that have served millions of beneficiaries. Additionally, I will highlight results from an earlier project on HIV prevention among youth experiencing homelessness in Los Angeles. Turning to conservation, I will highlight efforts for protecting endangered wildlife in national parks around the globe. To address challenges of ML+optimization common to all of these applications, we have advanced the state of the art in decision-focused learning, restless multi-armed bandits, influence maximization in social networks and green security games. In pushing this research agenda, our ultimate goal is to empower local communities and non-profits to directly benefit from advances in AI tools and techniques.

Downloads

Next from AAAI 2024

Effect Size Estimation for Duration Recommendation in Online Experiments: Leveraging Hierarchical Models and Objective Utility Approaches | VIDEO

Similar lecture

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning