Most state-of-the-art methods for medical image segmentation adopt the encoder-decoder architecture. However, this U-shaped framework still has limitations in capturing the non-local multi-scale information with a simple skip connection. To solve the problem, we firstly explore the potential weakness of skip connections in U-Net on multiple segmentation tasks, and find that i) not all skip connections are useful, each skip connection has different contribution; ii) the optimal combinations of skip connections are different, relying on the specific datasets. Based on our findings, we propose a new segmentation framework, named UDTransNet, to solve three semantic gaps in U-Net. Specifically, we propose a Dual Attention Transformer (DAT) module for capturing the channel- and spatial-wise relationships to better fuse the encoder features, and a Decoder-guided Recalibration Attention (DRA) module for effectively connecting the DAT tokens and the decoder features to eliminate the inconsistency. Hence, both modules establish a learnable connection to solve the semantic gaps between the encoder and the decoder, which leads to a high-performance segmentation model for medical images. Comprehensive experimental results indicate that our UDTransNet produces higher evaluation scores and finer segmentation results with relatively fewer parameters over the state-of-the-art segmentation methods on different public datasets. Code: https://github.com/McGregorWwww/UDTransNet.

Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be efficient and beneficial. Still, it is unclear to what extent human-AI collaboration will be successful, and how such teaming performs compared to humans or AI agents only. In this work, we show that learning from humans is effective and that human-AI collaboration outperforms human-controlled and fully autonomous AI agents in a complex simulation environment. In addition, we have developed a new simulator for critical infrastructure protection, focusing on a scenario where AI-powered drones and human teams collaborate to defend an airport against enemy drone attacks. We develop a user interface to allow humans to assist AI agents effectively. We demonstrated that agents learn faster while learning from policy correction compared to learning from humans or agents. Furthermore, human-AI collaboration requires lower mental and temporal demands, reduces human effort, and yields higher performance than if humans directly controlled all agents. In conclusion, we show that humans can provide helpful advice to the RL agents, allowing them to improve learning in a multi-agent setting.

We investigate interaction patterns for humans interacting with explainable and non-explainable robots. Non-explainable robots are here robots that do not explain their actions or non-actions, neither do they give any other feedback during interaction, in contrast to explainable robots. We video recorded and analyzed human behavior during a board game, where 20 humans verbally instructed either an explainable or non-explainable Pepper robot to move objects on the board. The transcriptions and annotations of the videos were transformed into transactions for association rule mining. Association rules discovered communication patterns in the interaction between the robots and the humans, and the most interesting rules were also tested with regular chi-square tests. Some statistically significant results are that there is a strong correlation between men and non-explainable robots and women and explainable robots, and that humans mirror some of the robot's modality. Our results also show that it is important to contextualize human interaction patterns, and that this can be easily done using association rules as an investigative tool. The presented results are important when designing robots that should adapt their behavior to become understandable for the interacting humans.

We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions of state-action features. This class is known to be more general than linear MDPs, where the transition kernel and the reward function are assumed to be linear functions of the feature vectors. As our first contribution, we show that the difference between the two classes is the presence of states in linearly $q^\pi$-realizable MDPs where for any policy, all the actions have approximately equal values, and skipping over these states by following an arbitrarily fixed policy in those states transforms the problem to a linear MDP. Based on this observation, we derive a novel (computationally inefficient) learning algorithm for linearly $q^\pi$-realizable MDPs that simultaneously learns what states should be skipped over and runs another learning algorithm on the linear MDP hidden in the problem. The method returns an $\epsilon$-optimal policy after $\text{polylog}(H, d)/\epsilon^2$ interactions with the MDP, where $H$ is the time horizon and $d$ is the dimension of the feature vectors, giving the first polynomial-sample-complexity online RL algorithm for this setting. The results are proved for the misspecified case, where the sample complexity is shown to degrade gracefully with the misspecification error.

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound biases from the observational data. Ignoring these biases and blindly fitting a model with the biased data could even negatively affect the online learning phase. In this work, we formulate this problem from a causal perspective. First, we categorize the biases into confounding bias and selection bias based on the causal structure they imply. Next, we extract the causal bound for each arm that is robust towards compound biases from biased observational data. The derived bounds contain the ground truth mean reward and can effectively guide the bandit agent to learn a nearly-optimal decision policy. We also conduct regret analysis in both contextual and non-contextual bandit settings and show that prior causal bounds could help consistently reduce the asymptotic regret.

AI companies are attempting to create AI systems that outperform humans at most economically valuable work. Current AI models are already automating away the livelihoods of some artists, actors, and writers. But there is infighting between those who prioritize current harms and future harms. We construct a game-theoretic model of conflict to study the causes and consequences of this disunity. Our model also helps explain why throughout history, stakeholders sharing a common threat have found it advantageous to unite against it, and why the common threat has in turn found it advantageous to divide and conquer. Under realistic parameter assumptions, our model makes several predictions that find preliminary corroboration in the historical-empirical record. First, current victims of AI-driven disempowerment need the future victims to realize that their interests are also under serious and imminent threat, so that future victims are incentivized to support current victims in solidarity. Second, the movement against AI-driven disempowerment can become more united, and thereby more likely to prevail, if members believe that their efforts will be successful as opposed to futile. Finally, the movement can better unite and prevail if its members are less myopic. Myopic members prioritize their future well-being less than their present well-being, and are thus disinclined to solidarily support current victims today at personal cost, even if this is necessary to counter the shared threat of AI-driven disempowerment.

We study worst-case VCG redistribution mechanism design for the public project problem. We use a multilayer perceptron (MLP) with ReLU activation to model the payment function and use mixed integer programming (MIP) to solve for the worst-case type profiles that maximally violate the mechanism design constraints. We collect these worst-case type profiles and use them as training samples to train toward better worst-case mechanisms. In practice, we require a tiny network structure for the above approach to scale. The Lottery Ticket Hypothesis states that a large network is likely to contain a "winning ticket" -- a much smaller subnetwork that "won the initialization lottery", which makes its training particularly effective. Motivated by this hypothesis, we train a large network and prune it into a tiny subnetwork. We run MIP-based worst-case training on the drawn subnetwork and evaluate the resulting mechanism's worst-case performance. If the subnetwork does not achieve good worst-case performance, then we record the type profiles that cause the current draw to be bad. To draw again, we restore the large network to its initial weights and prune using recorded type profiles from earlier draws, therefore avoiding drawing the same ticket twice. We expect to eventually encounter a tiny subnetwork that leads to effective training for our worst-case mechanism design task. Lastly, a by-product of multiple ticket draws is an ensemble of mechanisms with different worst cases, which improves the worst-case performance further. Using our approach, we find previously unknown optimal mechanisms for up to 5 agents. Our results confirm the tightness of existing theoretical upper bounds. For up to 20 agents, we derive significantly improved worst-case mechanisms, surpassing a long list of existing manual results.

A recurrent task in coordinated systems is managing (estimating, predicting, or controlling) signals that vary in space, such as distributed sensed data or computation outcomes. Especially in large-scale settings, the problem can be addressed through decentralised and situated computing systems: nodes can locally sense, process, and act upon signals, and coordinate with neighbours to implement collective strategies. Accordingly, in this work we devise distributed coordination strategies for the estimation of a spatial phenomenon through collaborative adaptive sampling. Our design is based on the idea of dynamically partitioning space into regions that compete and grow/shrink to provide accurate aggregate sampling. Such regions hence define a sort of virtualised space that is "fluid", since its structure adapts in response to pressure forces exerted by the underlying phenomenon. We provide an adaptive sampling algorithm in the field-based coordination framework, and prove it is self-stabilising and locally optimal. Finally, we verify by simulation that the proposed algorithm effectively carries out a spatially adaptive sampling while maintaining a tuneable trade-off between accuracy and efficiency.

Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the misuse of LLMs, such as plagiarism and spamming, have led to the development of multiple detectors, including fine-tuned classifiers and statistical methods. In this study, we equip LLMs with prompts, rather than relying on an external paraphraser, to evaluate the vulnerability of these detectors. We propose a novel Substitution-based In-Context example Optimization method (SICO) to automatically construct prompts for evading the detectors. SICO is cost-efficient as it requires only 40 human-written examples and a limited number of LLM inferences to generate a prompt. Moreover, once a task-specific prompt has been constructed, it can be universally used against a wide range of detectors. Extensive experiments across three real-world tasks demonstrate that SICO significantly outperforms the paraphraser baselines and enables GPT-3.5 to successfully evade six detectors, decreasing their AUC by 0.5 on average. Furthermore, a comprehensive human evaluation as well as a validation experiment in the wild show that the SICO-generated text achieves human-level readability and task completion rates. Finally, the strong performance of SICO exhibits its potential as a reliable evaluation tool for future detectors.

Reinforcement Learning (RL) has emerged as a highly effective technique for addressing various scientific and applied problems. Despite its success, certain complex tasks remain challenging to be addressed solely with a single model and algorithm. In response, ensemble reinforcement learning (ERL), a promising approach that combines the benefits of both RL and ensemble learning (EL), has gained widespread popularity. ERL leverages multiple models or training algorithms to comprehensively explore the problem space and possesses strong generalization capabilities. In this study, we present a comprehensive survey on ERL to provide readers with an overview of recent advances and challenges in the field. Firstly, we provide an introduction to the background and motivation for ERL. Secondly, we conduct a detailed analysis of strategies such as model selection and combination that have been successfully implemented in ERL. Subsequently, we explore the application of ERL, summarize the datasets, and analyze the algorithms employed. Finally, we outline several open questions and discuss future research directions of ERL. By offering guidance for future scientific research and engineering applications, this survey significantly contributes to the advancement of ERL.