arXiv subjects

Yang Yu

Publications and source records attributed to Yang Yu.

At least 325 records · Page 18Linked to original sources

arXiv2022

Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which only make use of the local context. In this paper, we propose a novel framework STswinCL that explores the complementary intra- and inter-video relations to boost segmentation performance, by progressively capturing the global context. We firstly develop a hierarchy Transformer to capture intra-video relation that includes richer spatial and temporal cues from neighbor pixels and previous frames. A joint space-time window shift scheme is proposed to efficiently aggregate these two cues into each pixel embedding. Then, we explore inter-video relation via pixel-to-pixel contrastive learning, which well structures the global embedding space. A multi-source contrast training objective is developed to group the pixel embeddings across videos with the ground-truth guidance, which is crucial for learning the global property of the whole data. We extensively validate our approach on two public surgical video benchmarks, including EndoVis18 Challenge and CaDIS dataset. Experimental results demonstrate the promising performance of our method, which consistently exceeds previous state-of-the-art approaches. Code is available at https://github.com/YuemingJin/STswinCL.

cs.CV↗

arXiv2022

LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates

In cooperative multi-agent reinforcement learning (MARL), where agents only have access to partial observations, efficiently leveraging local information is critical. During long-time observations, agents can build \textit{awareness} for teammates to alleviate the problem of partial observability. However, previous MARL methods usually neglect this kind of utilization of local information. To address this problem, we propose a novel framework, multi-agent \textit{Local INformation Decomposition for Awareness of teammates} (LINDA), with which agents learn to decompose local information and build awareness for each teammate. We model the awareness as stochastic random variables and perform representation learning to ensure the informativeness of awareness representations by maximizing the mutual information between awareness and the actual trajectory of the corresponding agent. LINDA is agnostic to specific algorithms and can be flexibly integrated to different MARL methods. Sufficient experiments show that the proposed framework learns informative awareness from local partial observations for better collaboration and significantly improves the learning performance, especially on challenging tasks.

cs.LG↗

arXiv2022

A Survey on Model-based Reinforcement Learning

Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error, making errors is always undesired in the real world. To improve the sample efficiency and thus reduce the errors, model-based reinforcement learning (MBRL) is believed to be a promising direction, which builds environment models in which the trial-and-errors can take place without real costs. In this survey, we take a review of MBRL with a focus on the recent progress in deep RL. For non-tabular environments, there is always a generalization error between the learned environment model and the real environment. As such, it is of great importance to analyze the discrepancy between policy training in the environment model and that in the real environment, which in turn guides the algorithm design for better model learning, model usage, and policy training. Besides, we also discuss the recent advances of model-based techniques in other forms of RL, including offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Moreover, we discuss the applicability and advantages of MBRL in real-world tasks. Finally, we end this survey by discussing the promising prospects for the future development of MBRL. We think that MBRL has great potential and advantages in real-world applications that were overlooked, and we hope this survey could attract more research on MBRL.

cs.LG↗

arXiv2022

Distributed Bootstrap for Simultaneous Inference Under High Dimensionality

We propose a distributed bootstrap method for simultaneous inference on high-dimensional massive data that are stored and processed with many machines. The method produces an $\ell_\infty$-norm confidence region based on a communication-efficient de-biased lasso, and we propose an efficient cross-validation approach to tune the method at every iteration. We theoretically prove a lower bound on the number of communication rounds $τ_{\min}$ that warrants the statistical accuracy and efficiency. Furthermore, $τ_{\min}$ only increases logarithmically with the number of workers and the intrinsic dimensionality, while nearly invariant to the nominal dimensionality. We test our theory by extensive simulation studies, and a variable screening task on a semi-synthetic dataset based on the US Airline On-Time Performance dataset. The code to reproduce the numerical results is available at GitHub: https://github.com/skchao74/Distributed-bootstrap.

stat.ME↗

arXiv2022

Context-Aware Sparse Deep Coordination Graphs

Learning sparse coordination graphs adaptive to the coordination dynamics among agents is a long-standing problem in cooperative multi-agent learning. This paper studies this problem and proposes a novel method using the variance of payoff functions to construct context-aware sparse coordination topologies. We theoretically consolidate our method by proving that the smaller the variance of payoff functions is, the less likely action selection will change after removing the corresponding edge. Moreover, we propose to learn action representations to effectively reduce the influence of payoff functions' estimation errors on graph construction. To empirically evaluate our method, we present the Multi-Agent COordination (MACO) benchmark by collecting classic coordination problems in the literature, increasing their difficulty, and classifying them into different types. We carry out a case study and experiments on the MACO and StarCraft II micromanagement benchmark to demonstrate the dynamics of sparse graph learning, the influence of graph sparseness, and the learning performance of our method. (The MACO benchmark and codes are publicly available at https://github.com/TonghanWang/CASEC-MACO-benchmark.)

cs.LG↗

arXiv2022

Model Generation with Provable Coverability for Offline Reinforcement Learning

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage. But due to the limitation under the offline setting, the learned model could not mimic real dynamics well enough to support reliable out-of-distribution exploration, which still hinders policy to generalize well. To narrow the gap, previous works roughly ensemble randomly initialized models to better approximate the real dynamics. However, such practice is costly and inefficient, and provides no guarantee on how well the real dynamics could be approximated by the learned models, which we name coverability in this paper. We actively address this issue by generating models with provable ability to cover real dynamics in an efficient and controllable way. To that end, we design a distance metric for dynamic models based on the occupancy of policies under the dynamics, and propose an algorithm to generate models optimizing their coverage for the real dynamics. We give a theoretical analysis on the model generation process and proves that our algorithm could provide enhanced coverability. As a downstream task, we train a dynamics-aware policy with minor or no conservative penalty, and experiments demonstrate that our algorithm outperforms prior offline methods on existing offline RL benchmarks. We also discover that policies learned by our method have better zero-shot transfer performance, implying their better generalization.

cs.LG↗

arXiv2022

Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning

Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting. In this paper, we propose Hybrid Value Estimation (HVE) to reduce value estimation error, which trades off bias and variance by balancing between the value estimation from offline data and the learned model. Theoretical analysis discloses that HVE enjoys a better error bound than the direct methods. HVE can be leveraged in both off-policy evaluation and offline reinforcement learning settings. We, therefore, provide two concrete algorithms Off-policy HVE (OPHVE) and Model-based Offline HVE (MOHVE), respectively. Empirical evaluations on MuJoCo tasks corroborate the theoretical claim. OPHVE outperforms other off-policy evaluation methods in all three metrics measuring the estimation effectiveness, while MOHVE achieves better or comparable performance with state-of-the-art offline reinforcement learning algorithms. We hope that HVE could shed some light on further research on reinforcement learning from fixed data.

cs.LG↗

arXiv2022

Offline Reinforcement Learning with Causal Structured World Models

Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully connected nets as world-models that map the states and actions to the next-step states. However, it is sensible that a world-model should adhere to the underlying causal effect such that it will support learning an effective policy generalizing well in unseen states. In this paper, We first provide theoretical results that causal world-models can outperform plain world-models for offline RL by incorporating the causal structure into the generalization error bound. We then propose a practical algorithm, oFfline mOdel-based reinforcement learning with CaUsal Structure (FOCUS), to illustrate the feasibility of learning and leveraging causal structure in offline RL. Experimental results on two benchmarks show that FOCUS reconstructs the underlying causal structure accurately and robustly. Consequently, it performs better than the plain model-based offline RL algorithms and other causal model-based RL algorithms.

cs.LG↗

arXiv2022

ZOOpt: Toolbox for Derivative-Free Optimization

Recent advances in derivative-free optimization allow efficient approximation of the global-optimal solutions of sophisticated functions, such as functions with many local optima, non-differentiable and non-continuous functions. This article describes the ZOOpt (Zeroth Order Optimization) toolbox that provides efficient derivative-free solvers and is designed easy to use. ZOOpt provides single-machine parallel optimization on the basis of python core and multi-machine distributed optimization for time-consuming tasks by incorporating with the Ray framework -- a famous platform for building distributed applications. ZOOpt particularly focuses on optimization problems in machine learning, addressing high-dimensional and noisy problems such as hyper-parameter tuning and direct policy search. The toolbox is maintained toward a ready-to-use tool in real-world machine learning tasks.

cs.LG↗

arXiv2022

Rethinking ValueDice: Does It Really Improve Performance?

Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvements: it beats the classical approach Behavioral Cloning (BC) under the offline setting, and it requires fewer interactions than GAIL under the online setting. Are these improvements benefited from more advanced algorithm designs? We answer this question by the following conclusions. First, we show that ValueDice could reduce to BC under the offline setting. Second, we verify that overfitting exists and regularization matters in the low-data regime. Specifically, we demonstrate that with weight decay, BC also nearly matches the expert performance as ValueDice does. The first two claims explain the superior offline performance of ValueDice. Third, we establish that ValueDice does not work when the expert trajectory is subsampled. Instead, the mentioned success of ValueDice holds when the expert trajectory is complete, in which ValueDice is closely related to BC that performs well as mentioned. Finally, we discuss the implications of our research for imitation learning studies beyond ValueDice.

cs.LG↗

arXiv2022

Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech

In this paper, we introduce a novel language identification system based on conformer layers. We propose an attentive temporal pooling mechanism to allow the model to carry information in long-form audio via a recurrent form, such that the inference can be performed in a streaming fashion. Additionally, we investigate two domain adaptation approaches to allow adapting an existing language identification model without retraining the model parameters for a new domain. We perform a comparative study of different model topologies under different constraints of model size, and find that conformer-based models significantly outperform LSTM and transformer based models. Our experiments also show that attentive temporal pooling and domain adaptation improve model accuracy.

eess.AS↗

arXiv2022

Mode-selective Single-dipole Excitation and Controlled Routing of Guided Waves in a Multi-mode Topological Waveguide

Topology-linked binary degrees of freedom of guided waves have been used to expand the channel capacity of and to ensure robust transmission through photonic waveguides. However, selectively exciting optical modes associated with the desired degree of freedom is challenging and typically requires spatially extended sources or filters. Both approaches are incompatible with the ultimate objective of developing compact mode-selective sources powered by single emitters. In addition, the implementation of highly desirable functionalities, such as controllable distribution of guided modes between multiple detectors, becomes challenging in highly-compact devices due to photon loss to reflections. Here, we demonstrate that a linearly-polarized dipole-like source can selectively excite a topologically robust edge mode with the desired valley degree of freedom. Reflection-free routing of valley-polarized edge modes into two spatially-separated detectors with reconfigurable splitting ratios is also presented. An optical implementation of such a source will have the potential to broaden the applications of topological photonic devices.

physics.optics↗

arXiv2022

Cancelling microwave crosstalk with fixed-frequency qubits

Scalable quantum information processing requires that modular gate operations can be executed in parallel. The presence of crosstalk decreases the individual addressability, causing erroneous results during simultaneous operations. For superconducting qubits which operate in the microwave regime, electromagnetic isolation is often limited due to design constraints, leading to signal crosstalk that can deteriorate the quality of simultaneous gate operations. Here, we propose and demonstrate a method based on AC Stark effect for calibrating the microwave signal crosstalk. The method is suitable for processors based on fixed-frequency qubits which are known for high coherence and simple control. The optimal compensation parameters can be reliably identified from a well-defined interference pattern. We implement the method on an array of 7 superconducting qubits, and show its effectiveness in removing the majority of crosstalk errors.

quant-ph↗

arXiv2022

Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library

Mathematical reasoning recently has been shown as a hard challenge for neural systems. Abilities including expression translation, logical reasoning, and mathematics knowledge acquiring appear to be essential to overcome the challenge. This paper demonstrates that some abilities can be achieved through abductive combination with discrete systems that have been programmed with human knowledge. On a mathematical reasoning dataset, we adopt the recently proposed abductive learning framework, and propose the ABL-Sym algorithm that combines the Transformer neural models with a symbolic mathematics library. ABL-Sym shows 9.73% accuracy improvement on the interpolation tasks and 47.22% accuracy improvement on the extrapolation tasks, over the state-of-the-art approaches. Online demonstration: http://math.polixir.ai

cs.LG↗

arXiv2022

A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle

Q-learning with function approximation could diverge in the off-policy setting and the target network is a powerful technique to address this issue. In this manuscript, we examine the sample complexity of the associated target Q-learning algorithm in the tabular case with a generative oracle. We point out a misleading claim in [Lee and He, 2020] and establish a tight analysis. In particular, we demonstrate that the sample complexity of the target Q-learning algorithm in [Lee and He, 2020] is $\widetilde{\mathcal O}(|\mathcal S|^2|\mathcal A|^2 (1-γ)^{-5}\varepsilon^{-2})$. Furthermore, we show that this sample complexity is improved to $\widetilde{\mathcal O}(|\mathcal S||\mathcal A| (1-γ)^{-5}\varepsilon^{-2})$ if we can sequentially update all state-action pairs and $\widetilde{\mathcal O}(|\mathcal S||\mathcal A| (1-γ)^{-4}\varepsilon^{-2})$ if $γ$ is further in $(1/2, 1)$. Compared with the vanilla Q-learning, our results conclude that the introduction of a periodically-frozen target Q-function does not sacrifice the sample complexity.

cs.LG↗

arXiv2022

Multi-Agent Policy Transfer via Task Relationship Modeling

Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous work on multi-agent transfer learning accommodate teams of different sizes, heavily relying on the generalization ability of neural networks for adapting to unseen tasks. We believe that the relationship among tasks provides the key information for policy adaptation. In this paper, we try to discover and exploit common structures among tasks for more efficient transfer, and propose to learn effect-based task representations as a common space of tasks, using an alternatively fixed training scheme. We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks. As a result, the proposed method can help transfer learned cooperation knowledge to new tasks after training on a few source tasks. We also find that fine-tuning the transferred policies help solve tasks that are hard to learn from scratch.

cs.AI↗

arXiv2022

Active Hierarchical Exploration with Stable Subgoal Representation Learning

Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general settings by concurrently learning hierarchical policies and subgoal representations. Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards. As the high-level policy selects subgoals in an online learned representation space, the dynamic change of the subgoal space severely hinders effective high-level exploration. In this paper, we propose a novel regularization that contributes to both stable and efficient subgoal representation learning. Building upon the stable representation, we design measures of novelty and potential for subgoals, and develop an active hierarchical exploration strategy that seeks out new promising subgoals and states without intrinsic rewards. Experimental results show that our approach significantly outperforms state-of-the-art baselines in continuous control tasks with sparse rewards.

cs.LG↗

arXiv2022

On Generalization of Adversarial Imitation Learning and Beyond

Despite massive empirical evaluations, one of the fundamental questions in imitation learning is still not fully settled: does AIL (adversarial imitation learning) provably generalize better than BC (behavioral cloning)? We study this open problem with tabular and episodic MDPs. For vanilla AIL that uses the direct maximum likelihood estimation, we provide both negative and positive answers under the known transition setting. For some MDPs, we show that vanilla AIL has a worse sample complexity than BC. The key insight is that the state-action distribution matching principle is weak so that AIL may generalize poorly even on visited states from the expert demonstrations. For another class of MDPs, vanilla AIL is proved to generalize well even on non-visited states. Interestingly, its sample complexity is horizon-free, which provably beats BC by a wide margin. Finally, we establish a framework in the unknown transition scenario, which allows AIL to explore via reward-free exploration strategies. Compared with the best-known online apprenticeship learning algorithm, the resulting algorithm improves the sample complexity and interaction complexity.

cs.LG↗