United States

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate the benefits of the method in Lifelong RL experiments.

AAAI 2021

Lipschitz Lifelong 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/).


AAAI 2023

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.

technical paper

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. 

We study decentralized stochastic linear bandits, where a network of N agents acts cooperatively to efficiently solve a linear bandit-optimization problem over a d-dimensional space.  For this problem, we propose DLUCB: a fully decentralized algorithm that minimizes the cumulative regret over the entire network. At each round of the algorithm each agent chooses its actions following an upper confidence bound (UCB) strategy and agents share information with their immediate neighbors through a carefully designed consensus procedure that repeats over cycles. Our analysis adjusts the duration of these communication cycles ensuring near-optimal regret performance O(d \log{NT}\sqrt{NT}) at a communication rate of O(dN^2) per round. The structure of the network affects the regret performance via a small additive term â€“ coined the regret of delay â€“ that depends on the spectral gap of the underlying graph. Notably, our results apply to arbitrary network topologies without a requirement for a dedicated agent acting as a server. In consideration of situations with high communication cost, we propose RC-DLUCB: a modification of DLUCB with rare communication among agents. The new algorithm trades off regret performance for a significantly reduced total communication cost of O(d^3N^5/2) over all T rounds. Finally, we show that our ideas extend naturally to the emerging, albeit more challenging, setting of safe bandits. For the recently studied problem of linear bandits with unknown linear safety constraints, we propose the first safe decentralized algorithm. Our study contributes towards applying bandit techniques in safety-critical distributed systems that repeatedly deal with unknown stochastic environments. We present numerical simulations for various network topologies that corroborate our theoretical findings.

Decentralized Multi-Agent Linear Bandits with Safety Constraints

We study MNL bandits, which is a variant of the traditional multi-armed bandit problem, under risk criteria. Unlike the ordinary expected revenue, risk criteria are more general goals widely used in industries and business. We design algorithms for a broad class of risk criteria, including but not limited to the well-known conditional value-at-risk, Sharpe ratio, and entropy risk, and prove that they suffer a near-optimal regret. As a complement, we also conduct experiments with both synthetic and real data to show the empirical performance of our proposed algorithms.

Near-Optimal MNL Bandits Under Risk Criteria

Deep learning models have achieved state-of-the-art performance in semantic image segmentation, but the results provided by fully automatic algorithms are not always guaranteed satisfactory to users. Interactive segmentation offers a solution by accepting user annotations on selective areas of the images to refine the segmentation results. However, most existing models only focus on correcting the current image's misclassified pixels, with no knowledge carried over to other images. In this work, we formulate interactive image segmentation as a continual learning problem and propose a framework to effectively learn from user annotations, aiming to improve the segmentation on both the current image and unseen images in future tasks while avoiding deteriorated performance on previously-seen images. It employs a probabilistic mask to control the neural network's kernel activation and extract the most suitable features for segmenting images in each task. We also apply a task-aware embedding to automatically infer the optimal kernel activation for initial segmentation and subsequent refinement. Interactions with users are guided through multi-source uncertainty estimation so that users can focus on the most important areas to minimize the overall manual annotation effort. Experiments are performed on both medical and natural image datasets to illustrate the proposed framework's effectiveness on basic segmentation performance, forward knowledge transfer, and backward knowledge transfer.

A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation

In this work,   we introduce a   Denser   Feature   Network(DenserNet) for visual localization. Our work provides three principal contributions.  First,  we develop a  convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps,  our method can produce more key point features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level an-notation other than positive and negative GPS-tagged image pairs.  We use a  weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation.  Finally,  our method is computationally efficient as our architecture has shared features and parameters during forwarding propagation. Our method is flexible and can be crafted on a  light-weighted backbone architecture to achieve appealing efficiency with a small penalty on accuracy. Extensive experiment results indicate that our method sets a  new state-of-the-art on four challenging large-scale localization benchmarks and three image retrieval benchmarks with the same level of supervision. The code is available at https://github.com/goodproj13/DenserNet

DenserNet: Weakly Supervised Visual Localization Using Multi-Scale Feature Aggregation

Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. Existing WS-TAL methods rely on deep features learned for action recognition. However, due to the mismatch between classification and localization, these features cannot distinguish the frequently co-occurring contextual background, i.e., the context, and the actual action instances. We term this challenge action-context confusion, and it will adversely affect the action localization accuracy. To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context. By explicitly accounting for action visual elements, the action instances can be localized more precisely without the distraction from the context. To facilitate the learning of these two feature subspaces with only video-level categorical labels, we leverage the predictions from both spatial and temporal streams for snippets grouping. In addition, an unsupervised learning task is introduced to make the proposed module focus on mining temporal information. The proposed approach outperforms state-of-the-art WS-TAL methods on three benchmarks, i.e., THUMOS14, ActivityNet v1.2 and v1.3 datasets.

Weakly Supervised Temporal Action Localization through Learning Explicit Subspaces for Action and Context

We revisit the fundamental problem of predicting a binary ground truth based on independent binary judgments provided by experts. When the accuracy levels of the experts are known, the problem can be solved easily through maximum likelihood estimation. We consider, however, a setting in which we are given only a ranking of the experts by their accuracy. Motivated by the worst-case approach to handle the missing information, we consider three objective functions and design efficient algorithms for optimizing them. In particular, the recently popular distortion objective leads to an intuitive new rule. We show that our algorithms perform well empirically using real and synthetic data in collaborative filtering and political prediction domains.

Aggregating Binary Judgments Ranked by Accuracy

In a data poisoning attack, an attacker modifies, deletes, and/or inserts some training examples to corrupt the learnt machine learning model. Bootstrap Aggregating (bagging) is a well known ensemble learning method,  which trains multiple base models on random subsamples of a training dataset using a base learning algorithm and uses majority vote to predict labels of testing examples. We prove the intrinsic certified robustness of bagging against data poisoning attacks. Specifically, we show that bagging with an arbitrary base learning algorithm provably predicts the same label for a testing example when the number of modified, deleted, and/or inserted training examples is bounded by a threshold. Moreover, we show that our derived threshold is tight if no assumptions on the base learning algorithm are made.  We evaluate our method on  MNIST and CIFAR10. For instance, our method achieves a certified accuracy of 91.1% on MNIST when arbitrarily modifying, deleting, and/or inserting 100 training examples. Code is available at: https://github.com/jjy1994/BaggingCertifyDataPoisoning.

Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks

The reinforcement learning (RL) framework formalizes the notion of learning with interactions. Many real-world problems have large state-spaces and/or action-spaces such as in Go, StarCraft, protein folding, and robotics or are non-Markovian, which cause significant challenges to RL algorithms. In this work we address the large action-space problem by sequentializing actions, which can reduce the action-space size significantly, even down to two actions at the expense of an increased planning horizon. We provide explicit and exact constructions and equivalence proofs for all quantities of interest for arbitrary history-based processes. In the case of MDPs, this could help RL algorithms that bootstrap. In this work we show how action-binarization in the non-MDP case can significantly improve Extreme State Aggregation (ESA) bounds. ESA allows casting any (non-MDP, non-ergodic, history-based) RL problem into a fixed-sized non-Markovian state-space with the help of a surrogate Markovian process. On the upside, ESA enjoys similar optimality guarantees as Markovian models do. But a downside is that the size of the aggregated state-space becomes exponential in the size of the action-space. In this work, we patch this issue by binarizing the action-space. We provide an upper bound on the number of states of this binarized ESA that is logarithmic in the original action-space size, a double-exponential improvement.

Exact Reduction of Huge Action Spaces in General Reinforcement Learning

In this paper, we propose a Meta Cooperative Learning (MCL) framework for task-oriented dialog systems (TDSs). Our model consists of an auxiliary KB reasoning task for learning meta KB knowledge, an auxiliary dialogue reasoning task for learning dialogue patterns, and a TDS task (primary task) that aims at not only retrieving accurate entities from KB but also generating natural responses, which are coordinated to achieve collective success in both retrieving accurate KB entities and generating human-like responses via meta learning. Concretely, the dialog generation model amalgamates complementary meta KB and dialog knowledge from two novel auxiliary reasoning tasks that together provide integrated guidance to build a high-quality TDS by adding regularization terms to force primary network to produce similar results to auxiliary networks. While MCL automatically learns appropriate labels for the two auxiliary reasoning tasks from the primary task, without requiring access to any further data. The key idea behind MCL is to use the performance of the primary task, which is trained alongside the auxiliary tasks in one iteration, to improve the auxiliary labels for the next iteration with meta learning. Experimental results on three benchmark datasets show that MCL can generate higher quality responses compared to several strong baselines in terms of both automatic and human evaluations. Code to reproduce the results in this paper is available at: https://github.com/siat-nlp/MCL.

Exploring Auxiliary Reasoning Tasks for Task-Oriented Dialog Systems with Meta Cooperative Learning

Hierarchically constructing micro (i.e., intra-sentence or inter-sentence) discourse structure trees using explicit boundaries (e.g., sentence and paragraph boundaries) has been proved to be an effective strategy. However, it is difficult to apply this strategy to document-level macro (i.e., inter-paragraph) discourse parsing, the more challenging task, due to the lack of explicit boundaries at the higher level. To alleviate this issue, we introduce a topic segmentation mechanism to detect implicit topic boundaries and then help the document-level macro discourse parser to construct better discourse trees hierarchically. In particular, our parser first splits a document into several sections using the topic boundaries that the topic segmentation detects. Then it builds a smaller and more accurate discourse sub-tree in each section and sequentially forms a whole tree for a document. The experimental results on both Chinese MCDTB and English RST-DT show that our proposed method outperforms the state-of-the-art baselines significantly.

Downloads

Next from AAAI 2021

Decentralized Multi-Agent Linear Bandits with Safety Constraints

Similar lecture

Hypernetworks for Zero-shot Transfer in Reinforcement Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Decentralized Multi-Agent Linear Bandits with Safety Constraints

Similar lecture

Hypernetworks for Zero-shot Transfer in Reinforcement Learning

Downloads