arXiv subjects

Tian Lan

Publications and source records attributed to Tian Lan.

At least 163 records · Page 9Linked to original sources

arXiv2024

Collaborative AI Teaming in Unknown Environments via Active Goal Deduction

With the advancements of artificial intelligence (AI), we're seeing more scenarios that require AI to work closely with other agents, whose goals and strategies might not be known beforehand. However, existing approaches for training collaborative agents often require defined and known reward signals and cannot address the problem of teaming with unknown agents that often have latent objectives/rewards. In response to this challenge, we propose teaming with unknown agents framework, which leverages kernel density Bayesian inverse learning method for active goal deduction and utilizes pre-trained, goal-conditioned policies to enable zero-shot policy adaptation. We prove that unbiased reward estimates in our framework are sufficient for optimal teaming with unknown agents. We further evaluate the framework of redesigned multi-agent particle and StarCraft II micromanagement environments with diverse unknown agents of different behaviors/rewards. Empirical results demonstrate that our framework significantly advances the teaming performance of AI and unknown agents in a wide range of collaborative scenarios.

cs.AI↗

arXiv2024

Aerial Tensile Perching and Disentangling Mechanism for Long-Term Environmental Monitoring

Aerial robots show significant potential for forest canopy research and environmental monitoring by providing data collection capabilities at high spatial and temporal resolutions. However, limited flight endurance hinders their application. Inspired by natural perching behaviours, we propose a multi-modal aerial robot system that integrates tensile perching for energy conservation and a suspended actuated pod for data collection. The system consists of a quadrotor drone, a slewing ring mechanism allowing 360° tether rotation, and a streamlined pod with two ducted propellers connected via a tether. Winding and unwinding the tether allows the pod to move within the canopy, and activating the propellers allows the tether to be wrapped around branches for perching or disentangling. We experimentally determined the minimum counterweights required for stable perching under various conditions. Building on this, we devised and evaluated multiple perching and disentangling strategies. Comparisons of perching and disentangling manoeuvres demonstrate energy savings that could be further maximized with the use of the pod or tether winding. These approaches can reduce energy consumption to only 22\% and 1.5\%, respectively, compared to a drone disentangling manoeuvre. We also calculated the minimum idle time required by the proposed system after the system perching and motor shut down to save energy on a mission, which is 48.9\% of the operating time. Overall, the integrated system expands the operational capabilities and enhances the energy efficiency of aerial robots for long-term monitoring tasks.

cs.RO↗

arXiv2024

Torus algebra and logical operators at low energy

Given a modular tensor category $\mathscr{C}$, we construct an associative algebra $\mathrm{Tor({\mathscr{C}}})$, which we call the torus algebra. We prove that the torus algebra is semisimple by explicitly constructing all the simple modules. Suppose that a topological ordered phase described by $\mathscr{C}$ is put on a torus. Physically, each simple module over $\mathrm{Tor({\mathscr{C}}})$ consists of the low energy states on the torus with one anyon excitation, or equivalently, the ground states on a punctured torus where the anyon is enclosed by the puncture. Elements in $\mathrm{Tor({\mathscr{C}}})$ can be physically interpreted as anyon hopping processes on the torus. We give the precise formula how an arbitrary logical operator on the low energy states on a torus can be realized by moving anyons on the torus. Our work thus provides a theoretical proposal that the low energy states on a torus can serve as topological qudits and one can arbitrarily manipulate them by moving anyons around.

cond-mat.str-el↗

arXiv2024

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent research advances from the simple chain-of-thought prompting to more complex ReAct and Reflection reasoning strategy; agent architecture also evolves from single agent generation to multi-agent conversation, as well as multi-LLM multi-agent group chat. However, with the existing intricate frameworks and libraries, creating and evaluating new reasoning strategies and agent architectures has become a complex challenge, which hinders research investigation into LLM agents. Thus, we open-source a new AI agent library, AgentLite, which simplifies this process by offering a lightweight, user-friendly platform for innovating LLM agent reasoning, architectures, and applications with ease. AgentLite is a task-oriented framework designed to enhance the ability of agents to break down tasks and facilitate the development of multi-agent systems. Furthermore, we introduce multiple practical applications developed with AgentLite to demonstrate its convenience and flexibility. Get started now at: \url{https://github.com/SalesforceAIResearch/AgentLite}.

cs.MA↗

arXiv2024

Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data

Bayesian optimization (BO) has established itself as a leading strategy for efficiently optimizing expensive-to-evaluate functions. Existing BO methods mostly rely on Gaussian process (GP) surrogate models and are not applicable to (doubly-stochastic) Gaussian Cox processes, where the observation process is modulated by a latent intensity function modeled as a GP. In this paper, we propose a novel maximum a posteriori inference of Gaussian Cox processes. It leverages the Laplace approximation and change of kernel technique to transform the problem into a new reproducing kernel Hilbert space, where it becomes more tractable computationally. It enables us to obtain both a functional posterior of the latent intensity function and the covariance of the posterior, thus extending existing works that often focus on specific link functions or estimating the posterior mean. Using the result, we propose a BO framework based on the Gaussian Cox process model and further develop a Nyström approximation for efficient computation. Extensive evaluations on various synthetic and real-world datasets demonstrate significant improvement over state-of-the-art inference solutions for Gaussian Cox processes, as well as effective BO with a wide range of acquisition functions designed through the underlying Gaussian Cox process model.

cs.LG↗

arXiv2023

ConcaveQ: Non-Monotonic Value Function Factorization via Concave Representations in Deep Multi-Agent Reinforcement Learning

Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-agent utilities. To ensure Individual-Global-Maximum property, existing works often focus on value factorization using monotonic functions, which are known to result in restricted representation expressiveness. In this paper, we analyze the limitations of monotonic factorization and present ConcaveQ, a novel non-monotonic value function factorization approach that goes beyond monotonic mixing functions and employs neural network representations of concave mixing functions. Leveraging the concave property in factorization, an iterative action selection scheme is developed to obtain optimal joint actions during training. It is used to update agents' local policy networks, enabling fully decentralized execution. The effectiveness of the proposed ConcaveQ is validated across scenarios involving multi-agent predator-prey environment and StarCraft II micromanagement tasks. Empirical results exhibit significant improvement of ConcaveQ over state-of-the-art multi-agent reinforcement learning approaches.

cs.MA↗

arXiv2023

Quantum Current and Holographic Categorical Symmetry

We establish the formulation for quantum current. Given a symmetry group $G$, let $\mathcal{C}:=\mathrm{Rep} G$ be its representation category. Physically, symmetry charges are objects of $\mathcal{C}$ and symmetric operators are morphisms in $\mathcal{C}$. The addition of charges is given by the tensor product of representations. For any symmetric operator $O$ crossing two subsystems, the exact symmetry charge transported by $O$ can be extracted. The quantum current is defined as symmetric operators that can transport symmetry charges over an arbitrary long distance. A quantum current exactly corresponds to an object in the Drinfeld center $Z_1(\mathcal{C})$. The condition for quantum currents to be superconducting is also specified, which corresponds to condensation of anyons in one higher dimension. To express the local conservation, the internal hom must be used to compute the charge difference, and the framework of enriched category is inevitable. To illustrate these ideas, we develop a rigorous scheme of renormalization in one-dimensional lattice systems and analyse the fixed-point models. It is proved that in the fixed-point models, superconducting quantum currents form a Lagrangian algebra in $Z_1(\mathcal{C})$ and the boundary-bulk correspondence is verified in the enriched setting. Overall, the quantum current provides a natural physical interpretation to the holographic categorical symmetry.

cond-mat.str-el↗

arXiv2023

RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning

Communication is crucial for solving cooperative Multi-Agent Reinforcement Learning tasks in partially observable Markov Decision Processes. Existing works often rely on black-box methods to encode local information/features into messages shared with other agents, leading to the generation of continuous messages with high communication overhead and poor interpretability. Prior attempts at discrete communication methods generate one-hot vectors trained as part of agents' actions and use the Gumbel softmax operation for calculating message gradients, which are all heuristic designs that do not provide any quantitative guarantees on the expected return. This paper establishes an upper bound on the return gap between an ideal policy with full observability and an optimal partially observable policy with discrete communication. This result enables us to recast multi-agent communication into a novel online clustering problem over the local observations at each agent, with messages as cluster labels and the upper bound on the return gap as clustering loss. To minimize the return gap, we propose the Return-Gap-Minimization Communication (RGMComm) algorithm, which is a surprisingly simple design of discrete message generation functions and is integrated with reinforcement learning through the utilization of a novel Regularized Information Maximization loss function, which incorporates cosine-distance as the clustering metric. Evaluations show that RGMComm significantly outperforms state-of-the-art multi-agent communication baselines and can achieve nearly optimal returns with few-bit messages that are naturally interpretable.

cs.AI↗

arXiv2023

Real-time Network Intrusion Detection via Decision Transformers

Many cybersecurity problems that require real-time decision-making based on temporal observations can be abstracted as a sequence modeling problem, e.g., network intrusion detection from a sequence of arriving packets. Existing approaches like reinforcement learning may not be suitable for such cybersecurity decision problems, since the Markovian property may not necessarily hold and the underlying network states are often not observable. In this paper, we cast the problem of real-time network intrusion detection as casual sequence modeling and draw upon the power of the transformer architecture for real-time decision-making. By conditioning a causal decision transformer on past trajectories, consisting of the rewards, network packets, and detection decisions, our proposed framework will generate future detection decisions to achieve the desired return. It enables decision transformers to be applied to real-time network intrusion detection, as well as a novel tradeoff between the accuracy and timeliness of detection. The proposed solution is evaluated on public network intrusion detection datasets and outperforms several baseline algorithms using reinforcement learning and sequence modeling, in terms of detection accuracy and timeliness.

cs.CR↗

arXiv2023

Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning

Next-generation wireless networks, such as edge intelligence and wireless distributed learning, face two critical challenges: communication efficiency and privacy protection. In this work, our focus is on addressing these issues in a distributed learning framework. We consider a new approach that simultaneously achieves communication efficiency and privacy protection by exploiting the privacy advantage offered by quantization. Specifically, we use a quantization scheme called \textbf{Gau}ssian \textbf{L}ayered \textbf{R}andomized \textbf{Q}uantization (Gau-LRQ) that compresses the raw model gradients using a layer multishift coupler. By adjusting the parameters of Gau-LRQ, we shape the quantization error to follow the expected Gaussian distribution, thus ensuring client-level differential privacy (CLDP). We demonstrate the effectiveness of our proposed Gau-LRQ in the distributed stochastic gradient descent (SGD) framework and theoretically quantify the trade-offs between communication, privacy, and convergence performance. We further improve the convergence performance by enabling dynamic private budget and quantization bit allocation. We achieve this by using an optimization formula that minimizes convergence error subject to the privacy budget constraint. We evaluate our approach on multiple datasets, including MNIST, CIFAR-10, and CIFAR-100, and show that our proposed method outperforms the baselines in terms of learning performance under various privacy constraints. Moreover, we observe that dynamic privacy allocation yields additional accuracy improvements for the models compared to the fixed scheme.

cs.DC↗

arXiv2023

RIDE: Real-time Intrusion Detection via Explainable Machine Learning Implemented in a Memristor Hardware Architecture

Deep Learning (DL) based methods have shown great promise in network intrusion detection by identifying malicious network traffic behavior patterns with high accuracy, but their applications to real-time, packet-level detections in high-speed communication networks are challenging due to the high computation time and resource requirements of Deep Neural Networks (DNNs), as well as lack of explainability. To this end, we propose a packet-level network intrusion detection solution that makes novel use of Recurrent Autoencoders to integrate an arbitrary-length sequence of packets into a more compact joint feature embedding, which is fed into a DNN-based classifier. To enable explainability and support real-time detections at micro-second speed, we further develop a Software-Hardware Co-Design approach to efficiently realize the proposed solution by converting the learned detection policies into decision trees and implementing them using an emerging architecture based on memristor devices. By jointly optimizing associated software and hardware constraints, we show that our approach leads to an extremely efficient, real-time solution with high detection accuracy at the packet level. Evaluation results on real-world datasets (e.g., UNSW and CIC-IDS datasets) demonstrate nearly three-nines detection accuracy with a substantial speedup of nearly four orders of magnitude.

cs.CR↗

arXiv2023

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction

Cross-device Federated Learning (FL) faces significant challenges where low-end clients that could potentially make unique contributions are excluded from training large models due to their resource bottlenecks. Recent research efforts have focused on model-heterogeneous FL, by extracting reduced-size models from the global model and applying them to local clients accordingly. Despite the empirical success, general theoretical guarantees of convergence on this method remain an open question. This paper presents a unifying framework for heterogeneous FL algorithms with online model extraction and provides a general convergence analysis for the first time. In particular, we prove that under certain sufficient conditions and for both IID and non-IID data, these algorithms converge to a stationary point of standard FL for general smooth cost functions. Moreover, we introduce the concept of minimum coverage index, together with model reduction noise, which will determine the convergence of heterogeneous federated learning, and therefore we advocate for a holistic approach that considers both factors to enhance the efficiency of heterogeneous federated learning.

cs.LG↗

arXiv2023

Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective

There are a number of diverging hypotheses about the neural text degeneration problem, i.e., generating repetitive and dull loops, which makes this problem both interesting and confusing. In this work, we aim to advance our understanding by presenting a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Subsequent experiments also demonstrate that by selectively dropping out the attention to repetitive words in training data, degeneration can be significantly minimized. Furthermore, our empirical analysis illustrates that prior works addressing the degeneration issue from various standpoints, such as the high-inflow words, the likelihood objective, and the self-reinforcement phenomenon, can be interpreted by one simple explanation. That is, penalizing the repetitions in training data is a common and fundamental factor for their effectiveness. Moreover, our experiments reveal that penalizing the repetitions in training data remains critical even when considering larger model sizes and instruction tuning.

cs.CL↗

arXiv2023

AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy

The widespread adoption of Federated Learning (FL), a privacy-preserving distributed learning methodology, has been impeded by the challenge of high communication overheads, typically arising from the transmission of large-scale models. Existing adaptive quantization methods, designed to mitigate these overheads, operate under the impractical assumption of uniform device participation in every training round. Additionally, these methods are limited in their adaptability due to the necessity of manual quantization level selection and often overlook biases inherent in local devices' data, thereby affecting the robustness of the global model. In response, this paper introduces AQUILA (adaptive quantization in device selection strategy), a novel adaptive framework devised to effectively handle these issues, enhancing the efficiency and robustness of FL. AQUILA integrates a sophisticated device selection method that prioritizes the quality and usefulness of device updates. Utilizing the exact global model stored by devices, it enables a more precise device selection criterion, reduces model deviation, and limits the need for hyperparameter adjustments. Furthermore, AQUILA presents an innovative quantization criterion, optimized to improve communication efficiency while assuring model convergence. Our experiments demonstrate that AQUILA significantly decreases communication costs compared to existing methods, while maintaining comparable model performance across diverse non-homogeneous FL settings, such as Non-IID data and heterogeneous model architectures.

cs.LG↗

arXiv2023

A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process

Learning rich skills under the option framework without supervision of external rewards is at the frontier of reinforcement learning research. Existing works mainly fall into two distinctive categories: variational option discovery that maximizes the diversity of the options through a mutual information loss (while ignoring coverage) and Laplacian-based methods that focus on improving the coverage of options by increasing connectivity of the state space (while ignoring diversity). In this paper, we show that diversity and coverage in unsupervised option discovery can indeed be unified under the same mathematical framework. To be specific, we explicitly quantify the diversity and coverage of the learned options through a novel use of Determinantal Point Process (DPP) and optimize these objectives to discover options with both superior diversity and coverage. Our proposed algorithm, ODPP, has undergone extensive evaluation on challenging tasks created with Mujoco and Atari. The results demonstrate that our algorithm outperforms state-of-the-art baselines in both diversity- and coverage-driven categories.

cs.LG↗

arXiv2023

Multi-agent Deep Covering Skill Discovery

The use of skills (a.k.a., options) can greatly accelerate exploration in reinforcement learning, especially when only sparse reward signals are available. While option discovery methods have been proposed for individual agents, in multi-agent reinforcement learning settings, discovering collaborative options that can coordinate the behavior of multiple agents and encourage them to visit the under-explored regions of their joint state space has not been considered. In this case, we propose Multi-agent Deep Covering Option Discovery, which constructs the multi-agent options through minimizing the expected cover time of the multiple agents' joint state space. Also, we propose a novel framework to adopt the multi-agent options in the MARL process. In practice, a multi-agent task can usually be divided into some sub-tasks, each of which can be completed by a sub-group of the agents. Therefore, our algorithm framework first leverages an attention mechanism to find collaborative agent sub-groups that would benefit most from coordinated actions. Then, a hierarchical algorithm, namely HA-MSAC, is developed to learn the multi-agent options for each sub-group to complete their sub-tasks first, and then to integrate them through a high-level policy as the solution of the whole task. This hierarchical option construction allows our framework to strike a balance between scalability and effective collaboration among the agents. The evaluation based on multi-agent collaborative tasks shows that the proposed algorithm can effectively capture the agent interactions with the attention mechanism, successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options, in terms of both faster exploration and higher task rewards.

cs.LG↗

arXiv2023

Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective

Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains where decisions have significant real-world consequences. In this paper, we propose a novel Advantage Actor-Critic with Reasoner (A2CR), which can be easily applied to Actor-Critic-based RL models and make them interpretable. A2CR consists of three interconnected networks: the Policy Network, the Value Network, and the Reasoner Network. By predefining and classifying the underlying purpose of the actor's actions, A2CR automatically generates a more comprehensive and interpretable paradigm for understanding the agent's decision-making process. It offers a range of functionalities such as purpose-based saliency, early failure detection, and model supervision, thereby promoting responsible and trustworthy RL. Evaluations conducted in action-rich Super Mario Bros environments yield intriguing findings: Reasoner-predicted label proportions decrease for ``Breakout" and increase for ``Hovering" as the exploration level of the RL algorithm intensifies. Additionally, purpose-based saliencies are more focused and comprehensible.

cs.AI↗

arXiv2023

Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning

Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforcement learning can be formulated as a sequence modeling problem and solved via supervised learning with approaches such as decision transformer. While these sequence-based methods achieve competitive results over return-to-go methods, especially on tasks that require longer episodes or with scarce rewards, importance sampling is not considered to correct the policy bias when dealing with off-policy data, mainly due to the absence of behavior policy and the use of deterministic evaluation policies. To this end, we propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation (DPE) in a unified framework with statistically proven properties on variance reduction. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks. Our method brings a performance improvements on selected methods which outperforms SOTA baselines in several tasks, demonstrating the advantages of enabling double policy estimation for sequence-modeled reinforcement learning.

cs.LG↗