United States

Offline reinforcement learning (RL) aims to learn policy from the passively collected offline dataset. Applying existing RL methods on the static dataset straightforwardly will raise distribution shift, causing these unconstrained RL methods to fail. To cope with the distribution shift problem, a common practice in offline RL is to constrain the policy explicitly or implicitly close to behavioral policy. However, the available dataset usually contains sub-optimal or inferior actions, constraining the policy near all these actions will make the policy inevitably learn inferior behaviors, limiting the performance of the algorithm. Based on this observation, we propose a weighted policy constraints (wPC) method that only constrains the learned policy to desirable behaviors, making room for policy improvement on other parts. Our algorithm outperforms existing state-of-the-art offline RL algorithms on the D4RL offline gym datasets. Moreover, the proposed algorithm is simple to implement with few hyper-parameters, making the proposed wPC algorithm a robust offline RL method with low computational complexity.

AAAI 2023

Weighted Policy Constraints for Offline Reinforcement Learning

online learning & bandits

reinforcement learning algorithms

imitation learning & inverse reinforcement learning

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.

poster

Multi-label classification (MLC), which assigns multiple labels to each instance, is crucial to domains from computer vision to text mining. Conventional methods for MLC require huge amounts of labeled data to capture complex dependencies between labels. However, such labeled datasets are expensive, or even impossible, to acquire. Worse yet, these pre-trained MLC models can only be used for the particular label set covered in the training data. Despite this severe limitation, few methods exist for expanding the set of labels predicted by pre-trained models. Instead, we acquire vast amounts of new labeled data and retrain a new model from scratch. Here, we propose combining the knowledge from multiple pre-trained models (teachers) to train a new student model that covers the union of the labels predicted by this set of teachers. This student supports a broader label set than any one of its teachers without using labeled data. We call this new problem knowledge amalgamation for multi-label classification. Our new method, Adaptive KNowledge Transfer (ANT), trains a student by learning from each teacher’s partial knowledge of label dependencies to infer the global dependencies between all labels across the teachers. We show that ANT succeeds in unifying label dependencies among teachers, outperforming five state-of-the-art methods on eight real-world datasets.

Knowledge Amalgamation for Multi-Label Classification via Label Dependency Transfer

Active Object Tracking (AOT) aims at keeping a specific relation between tracker and object(s) by autonomously controlling the motion system of a tracker given observations. It is an important research area widely used in various applications, such as mobile robots, intelligent city, autonomous driving, etc. However, it remains challenging to build a generalizable active tracker to robustly work across different scenarios, especially in those unstructured environments with cluttered obstacles and diverse layouts. To realize this, we argue that the key is to construct a state representation that can model the geometry structure of the surroundings and the dynamics of the target. To this end, we propose a framework to form a structure-aware motion representation by Reconstructing the Surroundings of the tracker and Predicting the Trajectory of the target, called RSPT. Moreover, we further enhance the generalization of the policy network by training in the asymmetric dueling mechanism. Empirical results in virtual environments show that the tracker with RSPT significantly outperforms the existing methods among unseen environments, especially in environments with cluttered obstacles and diverse layouts. We further deploy the RSPT in a real-world scenario, showing good generalization in sim-to-real transfer.

Towards Generalizable Active Object Tracking with Reconstructing Surroundings and Predicting Trajectory

Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of architecture-performance data is required to get a working predictor. In this paper, we focus on exploiting information in cheaper-to-obtain performance estimations (i.e., low-fidelity information) to mitigate the large data requirements of predictor training. Despite the intuitiveness of this idea, we observe that using inappropriate low-fidelity information even damages the prediction ability and different search spaces have different preferences for low-fidelity information types. To solve the problem and better fuse beneficial information provided by different types of low-fidelity information, we propose a novel dynamic ensemble predictor framework that comprises two steps. In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts. In the second step, we learn a gating network to dynamically output a set of weighting coefficients conditioned on each input neural architecture, which will be used to combine the predictions of different low-fidelity experts in a weighted sum. The overall predictor is optimized on a small set of actual architecture-performance data to fuse the knowledge from different low-fidelity experts to make the final prediction. We conduct extensive experiments across five search spaces with different architecture encoders under various experimental settings. For example, our methods can improve the Kendall's Tau correlation coefficient between actual performance and predicted scores from 0.2549 to 0.7064 with only 25 actual architecture-performance data on NDS-ResNet. Our method can easily be incorporated into existing predictor-based NAS frameworks to discover better architectures. Our method will be implemented in Mindspore, and the example code is published at https://github.com/A-LinCui/DELE.

Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"

We study the fair allocation of indivisible goods among agents with identical, additive valuations but individual budget constraints. Here, the indivisible goods--each with a specific size and value--need to be allocated such that the bundle assigned to each agent is of total size at most the agent's budget. Since envy-free allocation do not necessarily exist in the indivisible goods context, compelling relaxations--in particular, the notion of envy-freeness up to k goods (EFk)--have received significant attention in recent years. In an EFk allocation, each agent prefers its own bundle over that of any other agent, up to the removal of k goods, and the agents have similarly bounded envy against the charity (which corresponds to the set of all unallocated goods). Recently, Wu et al. (2021) showed that an allocation that satisfies the budget constraints and maximizes the Nash Social Welfare is 1/4-approximately EF1. However, the computation (or even existence) of exact EFk allocations remained an intriguing open problem.

We make notable progress towards this by proposing a simple, greedy, polynomial-time algorithm that computes EF2 allocations under budget constraints. Our algorithmic result  implies the universal existence of EF2 allocations in this fair division context. The analysis of the algorithm exploits intricate structural properties of envy-freeness. Interestingly, the same algorithm also provides EF1 guarantees for important special cases. Specifically, we settle the existence of EF1 allocations for instances in which: (i) the value of each good is proportional to its size, (ii) all the goods have the same size, or (iii) all the goods have the same value. Our EF2 result even extends to the setting wherein the goods' sizes are agent specific.

Finding Fair Allocations under Budget Constraints

Automated modeling assistance is indispensable to the AI planning being deployed in practice, notably in industry and other non-academic contexts. Yet, little progress has been made that goes beyond smart interfaces like programming environments. They focus on autocompletion, but lack intelligent support for guiding the modeler. As a theoretical foundation of a first step towards this direction, we study the computational complexity of correcting a flawed Hierarchical Task Network (HTN) planning domain. Specifically, a modeler provides a (white) list of plans that are supposed to be solutions, and likewise a (black) list of plans that shall not be solutions. We investigate the complexity of finding a set of (optimal or suboptimal) model corrections so that those plans are (respective not) solutions to the corrected model. More specifically, we factor out each hardness source that contributes towards NP-hardness, including one that we deem important for many other complexity investigations that go beyond our specific context of application. All complexities range between NP and Sigma-2-p, rising the hope for efficient practical tools in the future.

Was Fixing this Really That Hard? On the Complexity of Correcting HTN Domains

Following the success of the transformer architecture in the natural language domain, transformer-like architectures have been widely applied to the domain of symbolic music recently. Symbolic music and text, however, are two different modalities. Symbolic music contains multiple attributes, both absolute attributes (e.g., pitch) and relative attributes (e.g., pitch interval). These relative attributes shape human perception of musical motifs. These important relative attributes, however, are mostly ignored in existing symbolic music modelling methods with the main reason being the lack of a musically-meaningful embedding space where both the absolute and relative embeddings of the symbolic music tokens can be efficiently represented. In this paper, we propose the Fundamental Music Embedding (FME) for symbolic music based on a bias-adjusted sinusoidal encoding within which both the absolute and the relative attributes can be embedded and the fundamental musical properties (e.g., translational invariance) are explicitly preserved. Taking advantage of the proposed FME, we further propose a novel attention mechanism based on the relative index, pitch and onset embeddings (RIPO attention) such that the musical domain knowledge can be fully utilized for symbolic music modelling. Experiment results show that our proposed model: RIPO transformer which utilizes FME and RIPO attention outperforms the state-of-the-art transformers (i.e., music transformer, linear transformer) in a melody completion task. Moreover, using the RIPO transformer in a downstream music generation task, we notice that the notorious degeneration phenomenon no longer exists and the music generated by the RIPO transformer outperforms the music generated by state-of-the-art transformer models in both subjective and objective evaluations.

A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music Modeling

Advances in machine learning have enabled the prediction of immune system responses to prophylactic and therapeutic vaccines. However, the engineering task of designing vaccines remains a challenge. In particular, the genetic variability of the human immune system makes it difficult to design peptide vaccines that provide widespread immunity in vaccinated populations.  We introduce a framework for evaluating and designing peptide vaccines that uses probabilistic machine learning models, and demonstrate its ability to produce designs for a SARS-CoV-2 vaccine that outperform previous designs.  We provide a theoretical analysis of the approximability, scalability, and complexity of our framework.

Constrained Submodular Optimization for Vaccine Design

Multi-view Comprehensive Representation Learning (MCRL) aims to synthesize information from multiple views to learn comprehensive representations of data items. Prevalent deep MCRL methods typically concatenate synergistic view-specific representations or average aligned view-specific representations in the fusion stage. However, the performance of synergistic fusion methods inevitably degenerate or even fail when partial views are missing in real-world applications; the aligned based fusion methods usually cannot fully exploit the complementarity of multi-view data. To eliminate all these drawbacks, in this work we present a Progressive Deep Multi-view Fusion (PDMF) method. Considering the multi-view comprehensive representation should contain complete information and the view-specific data contain partial information, we deem that it is unstable to directly learn the mapping from partial information to complete information. Hence, PDMF employs a progressive learning strategy, which contains the pre-training and fine-tuning stages. In the pre-training stage, PDMF decodes the auxiliary comprehensive representation to the view-specific data. It also captures the consistency and complementarity by learning the relations between the dimensions of the auxiliary comprehensive representation and all views. In the fine-tuning stage, PDMF learns the mapping from the original data to the comprehensive representation with the help of the auxiliary comprehensive representation and relations. Experiments conducted on a synthetic toy dataset and 4 real-world datasets show that PDMF outperforms state-of-the-art baseline methods. The code is released at https://github.com/winterant/PDMF.

Progressive Deep Multi-view Comprehensive Representation Learning

Image super-resolution (SR) serves as a fundamental tool for the processing and transmission of multimedia data. Recently, Transformer-based models have achieved competitive performances in image SR. They divide images into fixed-size patches and apply self-attention on these patches to model long-range dependencies among pixels. However, this architecture design is originated for high-level vision tasks, which lacks design guideline from SR knowledge. In this paper, we aim to design a new attention block whose insights are from the interpretation of Local Attribution Map (LAM) for SR networks.  Specifically, LAM presents a hierarchical importance map where the most important pixels are located in a fine area of a patch and some less important pixels are spread in a coarse area of the whole image. To access pixels in the coarse area, instead of using a very large patch size, we propose a lightweight Global Pixel Access (GPA) module that applies cross-attention with the most similar patch in an image. In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details. In addition, a Cascaded Patch Division (CPD) strategy is proposed to enhance perceptual quality of recovered images. Extensive experiments suggest that our method outperforms state-of-the-art lightweight SR methods by a large margin. Code is available at \url{https://github.com/passerer/HPINet}.

From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-Resolution

This work presents Z-Mask, an effective and deterministic strategy to improve the adversarial robustness of convolutional networks against physically-realizable adversarial attacks.
The presented defense relies on specific Z-score analysis performed on the internal network features to detect and mask the pixels corresponding to adversarial objects in the input image. To this end, spatially contiguous activations are examined in shallow and deep layers to suggest potential adversarial regions. Such proposals are then aggregated through a multi-thresholding mechanism.
The effectiveness of Z-Mask is evaluated with an extensive set of experiments carried out on models for semantic segmentation and object detection. The evaluation is performed with both digital patches added to the input images and printed patches in the real world.
The results confirm that Z-Mask outperforms the state-of-the-art methods in terms of detection accuracy and overall performance of the networks under attack.
Furthermore, Z-Mask preserves its robustness against defense-aware attacks, making it suitable for safe and secure AI applications.

Downloads

Next from AAAI 2023

Knowledge Amalgamation for Multi-Label Classification via Label Dependency Transfer

Similar lecture

Adaptive Policy Learning for Offline-to-Online Reinforcement Learning