United States

In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode. Typical applications include robotic control with limited energy and video games with consumable items. In tasks with non-replenishable resources, we observe that popular RL methods such as soft actor critic suffer from poor sample efficiency. The major reason is that, they tend to exhaust resources fast and thus the subsequent exploration is severely restricted due to the absence of resources. To address this challenge, we first formalize the aforementioned problem as a resource-restricted reinforcement learning, and then propose a novel resource-aware exploration bonus (RAEB) to make reasonable usage of resources. An appealing feature of RAEB is that, it can significantly reduce unnecessary resource-consuming trials while effectively encouraging the agent to explore unvisited states. Experiments demonstrate that the proposed RAEB significantly outperforms state-of-the-art exploration strategies in resource-restricted reinforcement learning environments, improving the sample efficiency by up to an order of magnitude.

AAAI 2023

Efficient Exploration in Resource-Restricted Reinforcement Learning

reinforcement learning，efficient exploration，resource-restricted

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

Concept bottleneck models (CBMs) (Koh et al. 2020) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We extend CBMs to interactive prediction settings where the model can query a human collaborator for the label to some concepts. We develop an interaction policy that, at prediction time, chooses which concepts to request a label for so as to maximally improve the final prediction. We demonstrate that a simple policy combining concept prediction uncertainty and influence of the concept on the final prediction achieves strong performance and outperforms a static approach proposed in Koh et al. (2020) as well as active feature acquisition methods proposed in the literature. We show that the interactive CBM can achieve accuracy gains of 5-10% with only 5 interactions over competitive baselines on the Caltech UCSD Birds, CheXpert and OAI datasets.

Interactive Concept Bottleneck Models

Recently, reinforcement learning (RL) have achieved impressive performance in various domains. However, most RL frameworks oversimplify the problem by assuming a static, fixed-yet-known environment and often have difficulty generalizing to real-world scenarios. In this paper, we introduce a novel challenge with a more realistic setting, Incremental Reinforcement Learning, where the search space of the Markov Decision Process (MDP) continually expands. While previous methods usually suffer from the lack of efficiency in exploring the unseen transitions, especially with increasing search space, by random sampling or depending on the learning process, we present a new exploration framework named Dual-Adaptive ε-greedy Exploration (DAE) to address the challenge of Incremental RL. Specifically, DAE employs a Meta Policy and an Explorer Network to avoid redundant computation on those sufficiently learned samples. On one hand, the Meta Policy evaluates a state’s exploration convergence and adaptively assigns the value of ε. On the other hand, the Explorer Network estimates the occurrence of each action, conditional to the given state, for nominating the least-tried one to explore. Furthermore, we release a testbed based on a synthetic environment and the Atari benchmark to validate the effectiveness of any exploration algorithms under Incremental RL. Experimental results demonstrate that the proposed framework can efficiently learn the unseen transitions in new environments, leading to a superior performance, i.e., 81.12% higher, on averagely, over eight state-of-the-art methods.

Incremental Reinforcement Learning with Dual-Adaptive ε-greedy Exploration

Ad-hoc constraints (also called generic constraints) are important for modelling Constraint Satisfaction Problems (CSPs). Many representations have been proposed to define ad-hoc constraints, such as tables, decision diagrams, binary constraint trees, automatas and context-free grammars. However, prior works mainly focus on efficient Generalized Arc Consistency (GAC) propagators of ad-hoc constraints using the representations. In this paper, we ask a more fundamental question which bears on modelling constraints in a CSP as ad-hoc constraints, how the choice of constraints and operations affect tractability. Rather than ad-hoc constraints and their GAC propagators, our focus is on their expressive power in terms of succinctness (polysize) and cost of operations/queries (polytime). We use a large set of constraint families to investigate the expressive power of 14 existing ad-hoc constraints. We show a complete map of the succinctness of the ad-hoc constraints. We also present results on the tractability of applying various operations and queries on the ad-hoc constraints. Finally, we give case studies illustrating how our results can be useful for questions in the modelling of CSPs.

The Expressive Power of Ad-hoc Constraints for Modelling CSPs

Compared to point estimates calculated by standard neural networks, Bayesian neural networks (BNN) provide probability distributions over the output predictions and model parameters, i.e., the weights. Training the weight distribution of a BNN, however, is more involved due to the intractability of the underlying Bayesian inference problem and thus, requires efficient approximations. In this paper, we propose a novel approach for BNN learning via closed-form Bayesian inference. For this purpose, the calculation of the predictive distribution of the output and the update of the weight distribution are treated as Bayesian filtering and smoothing problems, where the weights are modeled as Gaussian random variables. This allows closed-form expressions for training the network's parameters in a sequential/online fashion without gradient descent. We demonstrate our method on several UCI datasets and compare it to the state of the art.

Kalman Bayesian Neural Networks for Closed-form Online Learning

Existing works on anomaly detection (AD) rely on clean labels from human annotators that are expensive to acquire in practice.  In this work, we propose a method to leverage weak/noisy labels (e.g., risk scores generated by machine rules for detecting malware) that are cheaper to obtain for anomaly detection. Specifically, we propose ADMoE, the first framework for anomaly detection algorithms to learn from noisy labels. In a nutshell, ADMoE leverages mixture-of-experts (MoE) architecture to encourage specialized and scalable learning from multiple noisy sources. It captures the similarities among noisy labels by sharing most model parameters, while encouraging specialization by building "expert" sub-networks. To further juice out the signals from noisy labels, ADMoE uses them as input features to facilitate expert learning. Extensive results on eight datasets (including a proprietary enterprise security dataset) demonstrate the effectiveness of ADMoE, where it brings up to 34% performance improvement over not using it. Also, it outperforms a total of 13 leading baselines with equivalent network parameters and FLOPS. Notably, ADMoE is model-agnostic to enable any neural network-based detection methods to handle noisy labels, where we showcase its results on both multiple-layer perceptron (MLP) and the leading AD method DeepSAD.

ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels

Recent progress in using machine learning models for reasoning tasks has been driven by novel model architectures, large scale pre-training protocols, and dedicated reasoning datasets for fine-tuning. In this work, to further pursue these advances, we introduce a new data generator for machine reasoning that integrates with an embodied agent. The generated data consists of templated text queries and answers, matched with world-states encoded into a database. The world-states are a result of both world dynamics and the actions of the agent. We show the results of several baseline models on instantiations of train sets. These include pre-trained language models fine-tuned on a text-formatted representation of the database, and graph-structured Transformers operating on a knowledge-graph representation of the database. We find that these models can answer some questions about the world-state, but struggle with others. These results hint at new research directions in designing neural reasoning models and database representations.

A Data Source for Reasoning Embodied Agents

Recent studies have demonstrated that existing deep neural networks (DNNs) on 3D point clouds are vulnerable to adversarial examples, especially under the white-box settings where the adversaries have access to model parameters. However, adversarial 3D point clouds generated by existing white-box methods have limited transferability across different DNN architectures. They have only minor threats in real-world scenarios under the black-box settings where the adversaries can only query the deployed victim model. In this paper, we revisit the transferability of adversarial 3D point clouds. We observe that an adversarial perturbation can be randomly factorized into two sub-perturbations, which are also likely to be adversarial perturbations. It motivates us to consider the effects of the perturbation and its sub-perturbations simultaneously to increase the transferability for sub-perturbations also contain helpful information. In this paper, we propose a simple yet effective attack method to generate more transferable adversarial 3D point clouds. Specifically, rather than simply optimizing the loss of perturbation alone, we combine it with its random factorization. We conduct experiments on benchmark dataset, verifying our method's effectiveness in increasing transferability while preserving high efficiency.

Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a self-driving car with a vision system drives from dawn to dusk, with the sky gradually darkening. Therefore, the system must be able to adapt to changes in ambient illuminations and continue to drive safely on the road. In this paper, we formulate such problems as Evolving Domain Generalization, where a model aims to generalize well on a target domain by discovering and leveraging the evolving pattern of the environment. We then propose Directional Domain Augmentation (DDA), which simulates the unseen target features by mapping source data as augmentations through a domain transformer. Specifically, we formulate DDA as a bi-level optimization problem and solve it through a novel meta-learning approach in the representation space. We evaluate the proposed method on both synthetic datasets and real-world datasets, and empirical results show that our approach can outperform other existing methods. 

Foresee What You Will Learn: Data Augmentation for Domain Generalizationin in Non-Stationary Environment

Most video anomaly detection methods discriminate events that deviate from normal patterns as anomalies. However, these methods are prone to interferences from event-irrelevant factors,  such as background textures and object scale variations,  incurring an increased false detection rate. In this paper, we propose to explicitly learn event-relevant factors to eliminate the interferences from event-irrelevant factors on anomaly predictions.  To this end, we introduce a causal generative model to separate the event-relevant factors and event-irrelevant ones in videos, and learn the prototypes of event-relevant factors in a memory augmentation module.   We design a causal objective function to optimize the causal generative model and develop a counterfactual learning strategy to guide anomaly predictions, which increases the influence of the event-relevant factors. The extensive experiments show the effectiveness of our method for video anomaly detection.

Learning Event-Relevant Factors for Video Anomaly Detection

Multi-scale features from backbone networks have been widely applied to recover object details in segmentation tasks. Generally, the multi-level features are fused in a certain manner for further pixel-level dense prediction. Whereas, the spatial structure information is not fully explored, that is similar nearby pixels can be used to complement each other. In this paper, we investigate a progressive neighborhood aggregation (PNA) framework to refine the semantic segmentation prediction, resulting in an end-to-end solution that can perform the coarse prediction and refinement in a unified network. Specifically, we first present a neighborhood aggregation module, the neighborhood similarity matrices for each pixel are estimated on multi-scale features, which are further used to progressively aggregate the high-level feature for recovering the spatial structure. In addition, to further integrate the high-resolution details into the aggregated feature, we apply a self-aggregation module on the low-level features to emphasize important semantic information for complementing losing spatial details. Extensive experiments on five segmentation datasets, including Pascal VOC 2012, CityScapes, COCO-Stuff 10k, DeepGlobe, and Trans10k, demonstrate that the proposed framework can be cascaded into existing segmentation models providing consistent improvements. In particular, our method achieves new state-of-the-art performances on two challenging datasets, DeepGlobe and Trans10k. The code is available at https://github.com/liutinglt/PNA.

Premium content

Efficient Exploration in Resource-Restricted Reinforcement Learning

Downloads

Next from AAAI 2023

Interactive Concept Bottleneck Models

Similar lecture

Spectral Feature Augmentation for Graph Contrastive Learning and Beyond