A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or underestimation of the cost constraint at each state. Therefore, we provide an approach that does not modify the trajectory based cost constraint and instead imitates ``good'' trajectories and avoids ``bad'' trajectories generated from incrementally improving policies. We employ an oracle that utilizes a reward threshold (which is varied with learning) and the overall cost constraint to label trajectories as ``good'' or ``bad''. A key advantage of our approach is that we are able to work from any starting policy or set of trajectories and improve on it. In an exhaustive set of experiments, we demonstrate that our approach is able to outperform top benchmark approaches for solving Constrained RL problems, with respect to expected cost, CVaR cost, or even unknown cost constraints.
相關內容
Decision-making, a complicated task requiring various types of abilities, presents an excellent framework for assessing Large Language Models (LLMs). Our research investigates LLMs' decision-making capabilities through the lens of a well-established field, Game Theory. We focus specifically on games that support the participation of more than two agents simultaneously. Subsequently, we introduce our framework, GAMA-Bench, including eight classical multi-agent games. We design a scoring scheme to assess a model's performance in these games quantitatively. Through GAMA-Bench, we investigate LLMs' robustness, generalizability, and enhancement strategies. Results reveal that while GPT-3.5 shows satisfying robustness, its generalizability is relatively limited. However, its performance can be improved through approaches such as Chain-of-Thought. Additionally, we conduct evaluations across various LLMs and find that GPT-4 outperforms other models on GAMA-Bench, achieving a score of 60.5. Moreover, Gemini-1.0-Pro and GPT-3.5 (0613, 1106, 0125) demonstrate similar intelligence on GAMA-Bench. The code and experimental results are made publicly available via //github.com/CUHK-ARISE/GAMABench.
Multi-modal foundation models such as CLIP have showcased impressive zero-shot capabilities. However, their applicability in resource-constrained environments is limited due to their large number of parameters and high inference time. While existing approaches have scaled down the entire CLIP architecture, we focus on training smaller variants of the image encoder, which suffices for efficient zero-shot classification. The use of synthetic data has shown promise in distilling representations from larger teachers, resulting in strong few-shot and linear probe performance. However, we find that this approach surprisingly fails in true zero-shot settings when using contrastive losses. We identify the exploitation of spurious features as being responsible for poor generalization between synthetic and real data. However, by using the image feature-based L2 distillation loss, we mitigate these problems and train students that achieve zero-shot performance which on four domain-specific datasets is on-par with a ViT-B/32 teacher model trained on DataCompXL, while featuring up to 92% fewer parameters.
Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem
Software engineers develop, fine-tune, and deploy deep learning (DL) models using a variety of development frameworks and runtime environments. DL model converters move models between frameworks and to runtime environments. Conversion errors compromise model quality and disrupt deployment. However, the failure characteristics of DL model converters are unknown, adding risk when using DL interoperability technologies. This paper analyzes failures in DL model converters. We survey software engineers about DL interoperability tools, use cases, and pain points (N=92). Then, we characterize failures in model converters associated with the main interoperability tool, ONNX (N=200 issues in PyTorch and TensorFlow). Finally, we formulate and test two hypotheses about structural causes for the failures we studied. We find that the node conversion stage of a model converter accounts for ~75% of the defects and 33% of reported failure are related to semantically incorrect models. The cause of semantically incorrect models is elusive, but models with behaviour inconsistencies share operator sequences. Our results motivate future research on making DL interoperability software simpler to maintain, extend, and validate. Research into behavioural tolerances and architectural coverage metrics could be fruitful.
Recent developments in Generative Artificial Intelligence (GenAI) have created a paradigm shift in multiple areas of society, and the use of these technologies is likely to become a defining feature of education in coming decades. GenAI offers transformative pedagogical opportunities, while simultaneously posing ethical and academic challenges. Against this backdrop, we outline a practical, simple, and sufficiently comprehensive tool to allow for the integration of GenAI tools into educational assessment: the AI Assessment Scale (AIAS). The AIAS empowers educators to select the appropriate level of GenAI usage in assessments based on the learning outcomes they seek to address. The AIAS offers greater clarity and transparency for students and educators, provides a fair and equitable policy tool for institutions to work with, and offers a nuanced approach which embraces the opportunities of GenAI while recognising that there are instances where such tools may not be pedagogically appropriate or necessary. By adopting a practical, flexible approach that can be implemented quickly, the AIAS can form a much-needed starting point to address the current uncertainty and anxiety regarding GenAI in education. As a secondary objective, we engage with the current literature and advocate for a refocused discourse on GenAI tools in education, one which foregrounds how technologies can help support and enhance teaching and learning, which contrasts with the current focus on GenAI as a facilitator of academic misconduct.
3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To mitigate this limitation, we present Holodeck, a system that generates 3D environments to match a user-supplied prompt fully automatedly. Holodeck can generate diverse scenes, e.g., arcades, spas, and museums, adjust the designs for styles, and can capture the semantics of complex queries such as "apartment for a researcher with a cat" and "office of a professor who is a fan of Star Wars". Holodeck leverages a large language model (i.e., GPT-4) for common sense knowledge about what the scene might look like and uses a large collection of 3D assets from Objaverse to populate the scene with diverse objects. To address the challenge of positioning objects correctly, we prompt GPT-4 to generate spatial relational constraints between objects and then optimize the layout to satisfy those constraints. Our large-scale human evaluation shows that annotators prefer Holodeck over manually designed procedural baselines in residential scenes and that Holodeck can produce high-quality outputs for diverse scene types. We also demonstrate an exciting application of Holodeck in Embodied AI, training agents to navigate in novel scenes like music rooms and daycares without human-constructed data, which is a significant step forward in developing general-purpose embodied agents.
A recent surge of users migrating from Twitter to alternative platforms, such as Mastodon, raised questions regarding what migration patterns are, how different platforms impact user behaviors, and how migrated users settle in the migration process. In this study, we elaborate on how we investigate these questions by collecting data over 10,000 users who migrated from Twitter to Mastodon within the first ten weeks following the ownership change of Twitter. Our research is structured in three primary steps. First, we develop algorithms to extract and analyze migration patterns. Second, by leveraging behavioral analysis, we examine the distinct architectures of Twitter and Mastodon to learn how user behaviors correspond with the characteristics of each platform. Last, we determine how particular behavioral factors influence users to stay on Mastodon. We share our findings of user migration, insights, and lessons learned from the user behavior study.
Code-recommendation systems, such as Copilot and CodeWhisperer, have the potential to improve programmer productivity by suggesting and auto-completing code. However, to fully realize their potential, we must understand how programmers interact with these systems and identify ways to improve that interaction. To seek insights about human-AI collaboration with code recommendations systems, we studied GitHub Copilot, a code-recommendation system used by millions of programmers daily. We developed CUPS, a taxonomy of common programmer activities when interacting with Copilot. Our study of 21 programmers, who completed coding tasks and retrospectively labeled their sessions with CUPS, showed that CUPS can help us understand how programmers interact with code-recommendation systems, revealing inefficiencies and time costs. Our insights reveal how programmers interact with Copilot and motivate new interface designs and metrics.
Adversarial inverse reinforcement learning (AIRL) stands as a cornerstone approach in imitation learning, yet it frequently faces criticisms from prior studies. In this paper, we rethink AIRL and respond to these criticisms. Criticism 1 lies in Inadequate Policy Imitation. We show that substituting the built-in algorithm with soft actor-critic (SAC) during policy updating (requires multi-iterations) significantly enhances the efficiency of policy imitation. Criticism 2 lies in Limited Performance in Transferable Reward Recovery Despite SAC Integration. While we find that SAC indeed exhibits a significant improvement in policy imitation, it introduces drawbacks to transferable reward recovery. We prove that the SAC algorithm itself is not feasible to disentangle the reward function comprehensively during the AIRL training process, and propose a hybrid framework, PPO-AIRL + SAC, for a satisfactory transfer effect. Criticism 3 lies in Unsatisfactory Proof from the Perspective of Potential Equilibrium. We reanalyze it from an algebraic theory perspective.
The customization of services in Fifth-generation (5G) and Beyond 5G (B5G) networks relies heavily on network slicing, which creates multiple virtual networks on a shared physical infrastructure, tailored to meet specific requirements of distinct applications, using Software Defined Networking (SDN) and Network Function Virtualization (NFV). It is imperative to ensure that network services meet the performance and reliability requirements of various applications and users, thus, service assurance is one of the critical components in network slicing. One of the key functionalities of network slicing is the ability to scale Virtualized Network Functions (VNFs) in response to changing resource demand and to meet Customer Service Level agreements (SLAs). In this paper, we introduce a proactive closed-loop algorithm for end-to-end network orchestration, designed to provide service assurance in 5G and B5G networks. We focus on dynamically scaling resources to meet key performance indicators (KPIs) specific to each network slice and operate in parallel across multiple slices, making it scalable and capable of managing completely automatically real-time service assurance. Through our experiments, we demonstrate that the proposed algorithm effectively fulfills service assurance requirements for different network slice types, thereby minimizing network resource utilization and reducing the over-provisioning of spare resources.
This study evaluates the performance of general-purpose AI, like ChatGPT, in legal question-answering tasks, highlighting significant risks to legal professionals and clients. It suggests leveraging foundational models enhanced by domain-specific knowledge to overcome these issues. The paper advocates for creating open-source legal AI systems to improve accuracy, transparency, and narrative diversity, addressing general AI's shortcomings in legal contexts.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191