Canada

In practice, it is essential to compare and rank candidate policies offline before real-world deployment for safety and reliability. Prior work seeks to solve this offline policy ranking (OPR) problem through value-based methods, such as Off-policy evaluation (OPE). However, they fail to analyze special case performance (e.g., worst or best cases), due to the lack of holistic characterization of policies’ performance. It is even more difficult to estimate precise policy values when the reward is not fully accessible under sparse settings. In this paper, we present Probabilistic Offline Policy Ranking (POPR), a framework to address OPR problems by leveraging expert data to characterize the probability of a candidate policy behaving like experts, and approximating its entire performance posterior distribution to help with ranking. POPR does not rely on value estimation, and the derived performance posterior can be used to distinguish candidates in worst-, best-, and average-cases. To estimate the posterior, we propose POPR-EABC, an Energy-based Approximate Bayesian Computation (ABC) method conducting likelihood-free inference. POPR-EABC reduces the heuristic nature of ABC by a smooth energy function, and improves the sampling efficiency by a pseudo-likelihood. We empirically demonstrate that POPR-EABC is adequate for evaluating policies in both discrete and continuous action spaces across various experiment environments, and facilitates probabilistic comparisons of candidate policies before deployment.

AAAI 2024

Probabilistic Offline Policy Ranking with Approximate Bayesian Computation

policy ranking

statistical estimation

reinforcement learning

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

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. 

In representation learning, a disentangled representation is highly desirable as it encodes generative factors of data in a separable and compact pattern. Researchers have advocated leveraging disentangled representations to complete downstream tasks with encouraging empirical evidence. This paper further investigates the necessity of disentangled representation in downstream applications. Specifically, we show that dimension-wise disentangled representations are unnecessary on a fundamental downstream task, abstract visual reasoning. We provide extensive empirical evidence against the necessity of disentanglement, covering multiple datasets, representation learning methods, and downstream network architectures. Furthermore, our findings suggest that the informativeness of representations is a better indicator of downstream performance than disentanglement. Finally, the positive correlation between informativeness and disentanglement explains the claimed usefulness of disentangled representations in previous works.  The source code is available at https://github.com/Richard-coder-Nai/disentanglement-lib-necessity.git

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge.Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by \myred{Xiezhi-Specialty with 14,041 questions and Xiezhi-Interdiscipline with 10,746 questions}. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management.

Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation

Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Built on offline RL algorithms, most O2O methods focus on the balance between RL objective and pessimism, or the utilization of offline and online samples. In this paper, from a novel perspective, we systematically study the challenges that remain in O2O RL and identify that the reason behind the slow improvement of the performance and the instability of online finetuning lies in the inaccurate Q-value estimation inherited from offline pretraining. Specifically, we demonstrate that the estimation bias and the inaccurate rank of Q-value cause a misleading signal for the policy update, making the standard offline RL algorithms, such as CQL and TD3-BC, ineffective in the online finetuning. Based on this observation, we address the problem of Q-value estimation by two techniques: (1) perturbed value update and (2) increased frequency of Q-value updates. The first technique smooths out biased Q-value estimation with sharp peaks, preventing early-stage policy exploitation of sub-optimal actions. The second one alleviates the estimation bias inherited from offline pretraining by accelerating learning. Extensive experiments on the MuJoco and Adroit environments demonstrate that the proposed method, named SO2, significantly alleviates Q-value estimation issues, and consistently improves the performance against the state-of-the-art methods by up to 83.1%.

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning | VIDEO

Since the rise of fair machine learning as a critical field of inquiry, many different notions on how to quantify and measure discrimination have been proposed in the literature. Some of these notions, however, were shown to be mutually incompatible. Such findings make it appear that numerous different kinds of fairness exist, thereby making a consensus on the appropriate measure of fairness harder to reach, hindering the applications of these tools in practice. In this paper, we investigate one of these key impossibility results that relates the notions of statistical and predictive parity. Specifically, we derive a new causal decomposition formula for the fairness measures associated with predictive parity, and obtain a novel insight into how this criterion is related to statistical parity through the legal doctrines of disparate treatment, disparate impact, and the notion of business necessity. Our results show that through a more careful causal analysis, the notions of statistical and predictive parity are not really mutually exclusive, but complementary and spanning a spectrum of fairness notions through the concept of business necessity. Finally, we demonstrate the importance of our findings on a real-world example.

Reconciling Predictive and Statistical Parity: A Causal Approach | VIDEO

Text-guided motion synthesis aims to generate 3D human motion that not only precisely reflects the textual description but reveals the motion details as much as possible. Pioneering methods explore the diffusion model for text-to-motion synthesis and obtain significant superiority. However, these methods conduct diffusion processes either on the raw data distribution or the low-dimensional latent space, which typically suffer from the problem of modality inconsistency or detail-scarce. To tackle this problem, we propose a novel \textbf{B}asic-to-\textbf{A}dvanced \textbf{H}ierarchical \textbf{D}iffusion \textbf{M}odel, named B2A-HDM, to collaboratively exploit low-dimensional and  high-dimensional diffusion models for high quality detailed motion synthesis. Specifically, the basic diffusion model in low-dimensional latent space provides the intermediate denoising result that to be consistent with the textual description, while the advanced diffusion model in high-dimensional latent space focuses on the following detail-enhancing denoising process. 
Besides, we introduce a multi-denoiser framework for the advanced diffusion model to ease the learning of high-dimensional model and fully explore the generative potential of the diffusion model. Quantitative and qualitative experiment results on two text-to-motion benchmarks (HumanML3D and KIT-ML) demonstrate that B2A-HDM can outperform existing state-of-the-art methods in terms of fidelity, modality consistency, and diversity.

Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model

Fairness-awareness has emerged as an essential building block for the responsible use of artificial intelligence in real applications. In many cases, inequity in performance is due to the change in distribution over different regions. While techniques have been developed to improve the transferability of fairness, a solution to the problem is not always feasible with no samples from the new regions, which is a bottleneck for pure data-driven attempts. Fortunately, physics-based mechanistic models have been studied for many problems with major social impacts. We propose SimFair, a physics-guided fairness-aware learning framework, which bridges the data limitation by integrating physical-rule-based simulation and inverse modeling into the training design. Using temperature prediction as an example, we demonstrate the effectiveness of the proposed SimFair in fairness preservation.

SimFair: Physics-Guided Fairness-Aware Learning with Simulation Models

The recent large language models (LLMs), e.g., ChatGPT, have been able to generate human-like and fluent responses when provided with specific instructions. While admitting the convenience brought by technological advancement, educators also have concerns that students might leverage LLMs to complete their writing assignments and pass them off as their original work. Although many AI content detection studies have been conducted as a result of such concerns, most of these prior studies modeled AI content detection as a classification problem, assuming that a text is either entirely human-written or entirely AI-generated. In this study, we investigated AI content detection in a rarely explored yet realistic setting where the text to be detected is collaboratively written by human and generative LLMs (termed as hybrid text for simplicity). We first formalized the detection task as identifying the transition points between human-written content and AI-generated content from a given hybrid text (boundary detection). We constructed a hybrid essay dataset by partially and randomly removing sentences from the original student-written essays and then instructing ChatGPT to fill in for the incomplete essays. Then we proposed a two-step detection approach where we (1) separated AI-generated content from human-written content during the encoder training process; and (2) calculated the distances between every two adjacent prototypes (a prototype is the mean of a set of consecutive sentences from the hybrid text in the embedding space) and assumed that the boundaries exist between the two adjacent prototypes that have the furthest distance from each other. Through extensive experiments, we observed the following main findings: (1) the proposed approach consistently outperformed the baseline methods across different experiment settings; (2) the encoder training process (i.e., step 1 of the above two-step approach) can significantly boost the performance of the proposed approach; (3) when detecting boundaries for single-boundary hybrid essays, the proposed approach could be enhanced by adopting a relatively large prototype size (i.e., the number of sentences needed to calculate a prototype), leading to a 22% improvement (against the best baseline method) in the In-Domain evaluation and an 18% improvement in the Out-of-Domain evaluation.

Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education

Dental caries has been widely recognized as one of the most prevalent chronic diseases in the field of public health. Despite advancements in automated diagnosis across various medical domains, it remains a substantial challenge for dental caries detection due to its inherent variability and intricacies. To bridge this gap, we release a hospital-scale panoramic dental X-ray benchmark, namely “CariesXrays”, to facilitate the advancements in high-precision computer-aided diagnosis for dental caries. It comprises 6,000 panoramic dental X-ray images, with a total of 13,783 instances of dental caries, all meticulously annotated by dental professionals. In this paper, we propose a novel Feature Pyramid Contrastive Learning (FPCL) framework, that jointly incorporates feature pyramid learning and contrastive learning within a unified diagnostic paradigm for automated dental caries detection. Specifically, a robust dual-directional feature pyramid network (D2D-FPN) is designed to adaptively capture rich and informative contextual information from multi-level feature maps, thus enhancing the generalization ability of caries detection across different scales. Furthermore, our model is augmented with an effective proposals-prototype contrastive regularization learning (P2P-CRL) mechanism, which can flexibly bridge the semantic gaps among diverse dental caries with varying appearances, resulting in high-quality dental caries proposals. Extensive experiments on our newly-established CariesXrays benchmark demonstrate the potential of FPCL to make a significant social impact on caries diagnosis.

CariesXrays: Enhancing Caries Detection in Hospital-Scale Panoramic Dental X-rays via Feature Pyramid Contrastive Learning

Many applications use computer vision to detect and count objects in massive image collections. However, automated methods may fail to deliver accurate counts, especially when the task is very difficult or requires a fast response time. For example, during disaster response, aid organizations aim to quickly count damaged buildings in satellite images to plan relief missions, but pre-trained building and damage detectors often perform poorly due to domain shifts. In such cases, there is a need for human-in-the-loop approaches to accurately count with minimal human effort. We propose DISCount -- a detector-based importance sampling framework for counting in large image collections. DISCount uses an imperfect detector and human screening to estimate low-variance unbiased counts. We propose techniques for counting over multiple spatial or temporal regions using a small amount of screening and estimate confidence intervals.  This enables end-users to stop screening when estimates are sufficiently accurate, which is often the goal in real-world applications.  We demonstrate our method with two applications: counting birds in radar imagery to understand responses to climate change, and counting damaged buildings in satellite imagery for damage assessment in regions struck by a natural disaster. On the technical side we develop variance reduction techniques based on control variates and prove the (conditional) unbiasedness of the estimators.  DISCount leads to a 9-12x reduction in the labeling costs to obtain the same error rates compared to naive screening for tasks we consider, and surpasses alternative covariate-based screening approaches.

DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling

Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization. RL is also very brittle; agents often overfit to their training environment and fail to generalize to new settings. Unsupervised environment design (UED) has been proposed as a solution to this problem, in which the agent trains in environments that have been specially selected to help it learn.  Previous UED algorithms focus on trying to train an RL agent that generalizes across a large distribution of environments. This is not necessarily desirable when we wish to prioritize performance in one environment over others. In this work, we will be examining the setting of robust RL building control, where we wish to train an RL agent that prioritizes performing well in normal weather while still being robust to extreme weather conditions. We demonstrate a novel UED algorithm, ActivePLR, that uses uncertainty-aware neural network architectures to generate new training environments at the limit of the RL agent's ability while being able to prioritize performance in a desired base environment. We show that ActivePLR is able to outperform state-of-the-art UED algorithms in minimizing energy usage while maximizing occupant comfort in the setting of building control.

Downloads

Next from AAAI 2024

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

Similar lecture

Chaining Value Functions for Off-Policy Learning