United States

Offline reinforcement learning (offline RL) considers problems where learning is performed using only previously collected samples and is helpful for the settings in which collecting new data is costly or risky. In model-based offline RL, the learner performs estimation (or optimization) using a model constructed according to the empirical transition frequencies. We analyze the sample complexity of vanilla model-based offline RL with dependent samples in the infinite-horizon discounted-reward setting. In our setting, the samples obey the dynamics of the Markov decision process and, consequently, may have interdependencies. Under no assumption of independent samples, we provide a high-probability, polynomial sample complexity bound for vanilla model-based off-policy evaluation that requires partial or uniform coverage. We extend this result to the off-policy optimization under uniform coverage. As a comparison to the model-based approach, we analyze the sample complexity of off-policy evaluation with vanilla importance sampling in the infinite-horizon setting. Finally, we provide an estimator that outperforms the sample-mean estimator for almost deterministic dynamics that are prevalent in reinforcement learning. 

AAAI 2023

On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples

planning with markov models (mdps

pomdps)

reinforcement learning theory

offline 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

With the increasing penetration of inverter-based renewable energy resources, deep reinforcement learning (DRL) has been proposed as one of the most promising solutions to realize real-time and autonomous control for future carbon-neutral power systems. In particular, DRL-based frequency control approaches have been extensively investigated in the literature to overcome the limitations of model-based approaches such as the computational cost and scalability for large-scale systems. Nevertheless, the real-world implementation of DRL-based frequency control methods is facing the following fundamental challenges: 1) safety guarantee during the learning and decision-making processes; 2) adaptability against the dynamic system operating conditions. To this end, this is the first work that proposes an Adaptive and Safe-Certified DRL (AdapSafe) algorithm for frequency control to simultaneously address the aforementioned challenges. In particular, a novel self-tuning control barrier function is designed to actively compensate the unsafe frequency control strategies under variational safety constraints and thus achieve guaranteed safety. Furthermore, the concept of meta-reinforcement learning is integrated to significantly enhance its adaptiveness in non-stationary power system environments without sacrificing the safety cost. Experiments are conducted based on GB 2030 power system, and the results demonstrate that the proposed AdapSafe exhibits superior performance in terms of its guaranteed safety in both training and test phases, as well as its considerable adaptability against the dynamics changes of system parameters.  

AdapSafe: Adaptive and Safe-Certified Deep Reinforcement Learning-Based Frequency Control for Carbon-neutral Power Systems

Given a large graph, can we learn its node embeddings from a smaller summary graph? What is the relationship between embeddings learned from original graphs and their summary graphs? Graph representation learning plays an important role in many graph mining applications, but learning em-beddings of large-scale graphs remains a challenge. Recent works try to alleviate it via graph summarization, which typ-ically includes the three steps: reducing the graph size by combining nodes and edges into supernodes and superedges,learning the supernode embedding on the summary graph and then restoring the embeddings of the original nodes. How-ever, the justification behind those steps is still unknown.
In this work, we propose GELSUMM, a well-formulated graph embedding learning framework based on graph sum-marization, in which we show the theoretical ground of learn-ing from summary graphs and the restoration with the three well-known graph embedding approaches in a closed form.Through extensive experiments on real-world datasets, we demonstrate that our methods can learn graph embeddings with matching or better performance on downstream tasks.This work provides theoretical analysis for learning node em-beddings via summarization and helps explain and under-stand the mechanism of the existing works.


A provable framework of learning graph embeddings via summarization

3D object detection with surrounding cameras has been a promising direction for autonomous driving. In this paper, we present SimMOD, a Simple baseline for Multi-camera Object Detection, to solve the problem. To incorporate multiview information as well as build upon previous efforts on monocular 3D object detection, the framework is built on sample-wise object proposals and designed to work in a twostage manner. First, we extract multi-scale features and generate the perspective object proposals on each monocular image. Second, the multi-view proposals are aggregated and then iteratively refined with multi-view and multi-scale visual features in the DETR3D-style. The refined proposals are endto-end decoded into the detection results. To further boost the performance, we incorporate the auxiliary branches alongside the proposal generation to enhance the feature learning. Also, we design the methods of target filtering and teacher forcing to promote the consistency of two-stage training. We conduct extensive experiments on the 3D object detection benchmark of nuScenes to demonstrate the effectiveness of SimMOD and achieve competitive performance. Code will be available at https://github.com/zhangyp15/SimMOD.

A Simple Baseline for Multi-Camera 3D Object Detection

We consider a sequential decision making problem where the agent faces the environment characterized by the stochastic discrete events and seeks an optimal intervention policy such that its long-term reward is maximized. This problem exists ubiquitously in social media, finance and health informatics but is rarely investigated by the conventional research in reinforcement learning. To this end, we present a novel framework of the model-based reinforcement learning where the agent's actions and observations  are  asynchronous stochastic discrete events occurring in continuous-time.  We model the dynamics of the environment by Hawkes process with external intervention control term and develop an algorithm to embed such process in the Bellman equation which guides the direction of the value gradient. We demonstrate the superiority of our method  in both synthetic simulator and real-data experiments. 

Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes

Recent studies have shown that the generalization ability of deep neural networks (DNNs) is closely related to the Fisher information matrix (FIM) calculated during the early training phase. Several methods have been proposed to regularize the FIM for increased generalization of DNNs. However, they cannot be used directly for Bayesian neural networks (BNNs) because the variable parameters of BNNs make it difficult to calculate the FIM. To address this problem, we achieve regularization of the FIM of BNNs by specifying a new suitable prior distribution called the inverse-reference (IR) prior. To regularize the FIM, the IR prior is derived as the inverse of the reference prior that imposes minimal prior knowledge on the parameters and maximizes the trace of the FIM. We demonstrate that the IR prior can enhance the generalization ability of BNNs for large-scale data over previously used priors while providing adequate uncertainty quantifications using various benchmark image datasets and BNN structures.

Inverse-Reference Priors for Fisher Regularization of Bayesian Neural Networks

As deep learning models become popular, there is a lot of need for deploying them to diverse device environments. Because it is costly to develop and optimize a neural network for every single environment, there is a line of research to search neural networks for multiple target environments efficiently. However, existing works for such a situation still suffer from requiring many GPUs and expensive costs. Motivated by this, we propose a novel neural network optimization framework named Bespoke for low-cost deployment. Our framework searches for a lightweight model by replacing parts of an original model with randomly selected alternatives, each of which comes from a pretrained neural network or the original model. In the practical sense, Bespoke has two significant merits. One is that it requires near zero cost for designing the search space of neural networks. The other merit is that it exploits the sub-networks of public pretrained neural networks, so the total cost is minimal compared to the existing works. We conduct experiments exploring Bespoke's the merits, and the results show that it finds efficient models for multiple targets with meager cost.

Bespoke: A Block-Level Neural Network Optimization Framework for Low-Cost Deployment

Face-based speech synthesis provides a practical solution to generate voices from human faces. However, directly using 2D face images leads to the problems of uninterpretability and entanglement. In this paper, to address the issues, we introduce 3D face shape which (1) has an anatomical relationship between voice characteristics, partaking in the ``bone conduction" of human timbre production, and (2) is naturally independent of irrelevant factors by excluding the blending process. 
We devise a three-stage framework to generate speech from 3D face shapes. Fully considering timbre production in anatomical and acquired terms, our framework incorporates three additional relevant attributes including face texture, facial features, and demographics. Experiments and subjective tests demonstrate our method can generate utterances matching faces well, with good audio quality and voice diversity. We also explore and visualize how the voice changes with the face. Case studies show that our method upgrades the face-voice inference to personalized custom-made voice creating, revealing a promising prospect in virtual human and dubbing applications.

What Does Your Face Sound Like? 3D Face Shape Towards Voice

Multivariate time series forecasting with hierarchical structure
is widely used in real-world applications, e.g., sales
predictions for the geographical hierarchy formed by cities,
states, and countries. The hierarchical time series (HTS) forecasting
includes two sub-tasks, i.e., forecasting and reconciliation.
In the previous works, hierarchical information is only
integrated in the reconciliation step to maintain coherency,
but not in forecasting step for accuracy improvement. In this
paper, we propose two novel tree-based feature integration
mechanisms, i.e., top-down convolution and bottom-up attention
to leverage the information of the hierarchical structure
to improve the forecasting performance. Moreover, unlike
most previous reconciliation methods which either rely
on strong assumptions or focus on coherent constraints only,
we utilize deep neural optimization networks, which not only
achieve coherency without any assumptions, but also allow
more flexible and realistic constraints to achieve task-based
targets, e.g., lower under-estimation penalty and meaningful
decision-making loss to facilitate the subsequent downstream
tasks. Experiments on real-world datasets demonstrate that
our tree-based feature integration mechanism achieves superior
performances on hierarchical forecasting tasks compared
to the state-of-the-art methods, and our neural optimization
networks can be applied to real-world tasks effectively without
any additional effort under coherence and task-based constraints.

SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies

Semantic scene completion (SSC) aims to complete a partial 3D scene and predict its semantics simultaneously. Most existing works adopt the voxel representations, thus suffering from the growth of memory and computation cost as the voxel resolution increases. Though a few works attempt to solve SSC from the perspective of 3D point clouds, they have not fully exploited the correlation and complementarity between the two tasks of scene completion and semantic segmentation. In our work, we present CasFusionNet, a novel cascaded network for point cloud semantic scene completion by dense feature fusion. Specifically, we design (i) a global completion module (GCM) to produce an upsampled and completed but coarse point set, (ii) a semantic segmentation module (SSM) to predict the per-point semantic labels of the completed points generated by GCM, and (iii) a local refinement module (LRM) to further refine the coarse completed points and the associated labels from a local perspective. We organize the above three modules via dense feature fusion in each level, and cascade a total of four levels, where we also employ feature fusion between each level for sufficient information usage. Both quantitative and qualitative results on our compiled two point-based datasets validate the effectiveness and superiority of our CasFusionNet compared to state-of-the-art methods in terms of both scene completion and semantic segmentation. The codes and datasets are available at: https://github.com/JinfengX/CasFusionNet.

CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion

Conventional graph neural networks (GNNs) are often confronted with fairness issues that may stem from their input, including node attributes and neighbors surrounding a node. While several recent approaches have been proposed to eliminate the bias rooted in sensitive attributes, they ignore the other key input of GNNs, namely the neighbors of a node, which can introduce bias since GNNs hinge on neighborhood structures to generate node representations. In particular, the varying neighborhood structures across nodes, manifesting themselves in drastically different node degrees, give rise to the diverse behaviors of nodes and biased outcomes. In this paper, we first define and generalize the degree bias using a generalized definition of node degree as a manifestation and quantification of different multi-hop structures around different nodes. To address the bias in the context of node classification, we propose a novel GNN framework called Generalized Degree Fairness-centric Graph Neural Network (DegFairGNN). Specifically, in each GNN layer, we employ a learnable debiasing function to generate debiasing contexts, which modulate the layer-wise neighborhood aggregation to eliminate the degree bias originating from the diverse degrees among nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our model on both accuracy and fairness metrics.

On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples

Downloads

Next from AAAI 2023

AdapSafe: Adaptive and Safe-Certified Deep Reinforcement Learning-Based Frequency Control for Carbon-neutral Power Systems

Similar lecture

Safe Policy Improvement for POMDPs via Finite-State Controllers