A major challenge in decision making domains with large state spaces is to effectively select actions which maximize utility. In recent years, approaches such as reinforcement learning (RL) and search algorithms have been successful to tackle this issue, despite their differences. RL defines a learning framework that an agent explores and interacts with. Search algorithms provide a formalism to search for a solution. However, it is often difficult to evaluate the performances of such approaches in a practical way. Motivated by this problem, we focus on one game domain, i.e., Connect-4, and develop a novel evolutionary framework to evaluate three classes of algorithms: RL, Minimax and Monte Carlo tree search (MCTS). The contribution of this paper is threefold: i) we implement advanced versions of these algorithms and provide a systematic comparison with their standard counterpart, ii) we develop a novel evaluation framework, which we call the Evolutionary Tournament, and iii) we conduct an extensive evaluation of the relative performance of each algorithm to compare our findings. We evaluate different metrics and show that MCTS achieves the best results in terms of win percentage, whereas Minimax and Q-Learning are ranked in second and third place, respectively, although the latter is shown to be the fastest to make a decision.
相關內容
State machines are used in engineering many types of software-intensive systems. UML State Machines extend simple finite state machines with powerful constructs. Among the many extensions, there is one seemingly simple and innocent language construct that fundamentally changes state machines' reactive model of computation: doActivity behaviors. DoActivity behaviors describe behavior that is executed independently from the state machine once entered in a given state, typically modeling complex computation or communication as background tasks. However, the UML specification or textbooks are vague about how the doActivity behavior construct should be appropriately used. This lack of guidance is a severe issue as, when improperly used, doActivities can cause concurrent, non-deterministic bugs that are especially challenging to find and could ruin a seemingly correct software design. The Precise Semantics of UML State Machines (PSSM) specification introduced detailed operational semantics for state machines. To the best of our knowledge, there is no rigorous review yet of doActivity's semantics as specified in PSSM. We analyzed the semantics by collecting evidence from cross-checking the text of the specification, its semantic model and executable test cases, and the simulators supporting PSSM. We synthesized insights about subtle details and emergent behaviors relevant to tool developers and advanced modelers. We reported inconsistencies and missing clarifications in more than 20 issues to the standardization committee. Based on these insights, we studied 11 patterns for doActivities detailing the consequences of using a doActivity in a given situation and discussing countermeasures or alternative design choices. We hope that our analysis of the semantics and the patterns help vendors develop conformant simulators or verification tools and engineers design better state machine models.
In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this article reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic, or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.
Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equivariance is fixed to the symmetry of the whole group, limiting adaptability to diverse partial symmetries in real-world datasets, such as limited rotation symmetry of handwritten digit images and limited color-shift symmetry of flower images. Recent efforts address this limitation, one example being Partial G-CNN which restricts the output group space of convolution layers to break full equivariance. However, such an approach still fails to adjust equivariance levels across data. In this paper, we propose a novel approach, Variational Partial G-CNN (VP G-CNN), to capture varying levels of partial equivariance specific to each data instance. VP G-CNN redesigns the distribution of the output group elements to be conditioned on input data, leveraging variational inference to avoid overfitting. This enables the model to adjust its equivariance levels according to the needs of individual data points. Additionally, we address training instability inherent in discrete group equivariance models by redesigning the reparametrizable distribution. We demonstrate the effectiveness of VP G-CNN on both toy and real-world datasets, including MNIST67-180, CIFAR10, ColorMNIST, and Flowers102. Our results show robust performance, even in uncertainty metrics.
The tie-knotting task is highly challenging due to the tie's high deformation and long-horizon manipulation actions. This work presents TieBot, a Real-to-Sim-to-Real learning from visual demonstration system for the robots to learn to knot a tie. We introduce the Hierarchical Feature Matching approach to estimate a sequence of tie's meshes from the demonstration video. With these estimated meshes used as subgoals, we first learn a teacher policy using privileged information. Then, we learn a student policy with point cloud observation by imitating teacher policy. Lastly, our pipeline learns a residual policy when the learned policy is applied to real-world execution, mitigating the Sim2Real gap. We demonstrate the effectiveness of TieBot in simulation and the real world. In the real-world experiment, a dual-arm robot successfully knots a tie, achieving 50% success rate among 10 trials. Videos can be found //tiebots.github.io/.
User intentions are typically formalized as evaluation rewards to be maximized when fine-tuning language models (LMs). Existing alignment methods, such as Direct Preference Optimization (DPO), are mainly tailored for pairwise preference data where rewards are implicitly defined rather than explicitly given. In this paper, we introduce a general framework for LM alignment, leveraging Noise Contrastive Estimation (NCE) to bridge the gap in handling reward datasets explicitly annotated with scalar evaluations. Our framework comprises two parallel algorithms, NCA and InfoNCA, both enabling the direct extraction of an LM policy from reward data as well as preference data. Notably, we show that the DPO loss is a special case of our proposed InfoNCA objective under pairwise preference settings, thereby integrating and extending current alignment theories. By comparing NCA and InfoNCA, we demonstrate that the well-observed decreasing-likelihood trend of DPO/InfoNCA is caused by their focus on adjusting relative likelihood across different responses. In contrast, NCA optimizes the absolute likelihood for each response, thereby effectively preventing the chosen likelihood from decreasing. We evaluate our methods in both reward and preference settings with Mistral-8*7B and 7B models. Experiments suggest that InfoNCA/NCA surpasses various preference baselines when reward datasets are available. We also find NCA significantly outperforms DPO in complex reasoning tasks like math and coding.
Personalized recommendation serves as a ubiquitous channel for users to discover information tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item matching, potentially overlooking the nuanced essence of raw item contents across multiple modalities such as text, image, audio, and video. This underutilization of multimodal data poses a limitation to recommender systems, especially in multimedia services like news, music, and short-video platforms. The recent advancements in large multimodal models offer new opportunities and challenges in developing content-aware recommender systems. This survey seeks to provide a comprehensive exploration of the latest advancements and future trajectories in multimodal pretraining, adaptation, and generation techniques, as well as their applications in enhancing recommender systems. Furthermore, we discuss current open challenges and opportunities for future research in this dynamic domain. We believe that this survey, alongside the curated resources, will provide valuable insights to inspire further advancements in this evolving landscape.
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns. Addressing such concerns, alignment technologies were introduced to make these models conform to human preferences and values. Despite considerable advancements in the past year, various challenges lie in establishing the optimal alignment strategy, such as data cost and scalable oversight, and how to align remains an open question. In this survey paper, we comprehensively investigate value alignment approaches. We first unpack the historical context of alignment tracing back to the 1920s (where it comes from), then delve into the mathematical essence of alignment (what it is), shedding light on the inherent challenges. Following this foundation, we provide a detailed examination of existing alignment methods, which fall into three categories: Reinforcement Learning, Supervised Fine-Tuning, and In-context Learning, and demonstrate their intrinsic connections, strengths, and limitations, helping readers better understand this research area. In addition, two emerging topics, personal alignment, and multimodal alignment, are also discussed as novel frontiers in this field. Looking forward, we discuss potential alignment paradigms and how they could handle remaining challenges, prospecting where future alignment will go.
Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are abundant AI models available for different domains and modalities, they cannot handle complicated AI tasks. Considering large language models (LLMs) have exhibited exceptional ability in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks and language could be a generic interface to empower this. Based on this philosophy, we present HuggingGPT, a framework that leverages LLMs (e.g., ChatGPT) to connect various AI models in machine learning communities (e.g., Hugging Face) to solve AI tasks. Specifically, we use ChatGPT to conduct task planning when receiving a user request, select models according to their function descriptions available in Hugging Face, execute each subtask with the selected AI model, and summarize the response according to the execution results. By leveraging the strong language capability of ChatGPT and abundant AI models in Hugging Face, HuggingGPT is able to cover numerous sophisticated AI tasks in different modalities and domains and achieve impressive results in language, vision, speech, and other challenging tasks, which paves a new way towards artificial general intelligence.
Multi-agent influence diagrams (MAIDs) are a popular form of graphical model that, for certain classes of games, have been shown to offer key complexity and explainability advantages over traditional extensive form game (EFG) representations. In this paper, we extend previous work on MAIDs by introducing the concept of a MAID subgame, as well as subgame perfect and trembling hand perfect equilibrium refinements. We then prove several equivalence results between MAIDs and EFGs. Finally, we describe an open source implementation for reasoning about MAIDs and computing their equilibria.
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We demonstrate that commonly used metric learning approaches do not optimally leverage the feature hierarchies learned in a Convolutional Neural Network (CNN), especially when applied to the task of geometric feature matching. While a metric loss applied to the deepest layer of a CNN, is often expected to yield ideal features irrespective of the task, in fact the growing receptive field as well as striding effects cause shallower features to be better at high precision matching tasks. We leverage this insight together with explicit supervision at multiple levels of the feature hierarchy for better regularization, to learn more effective descriptors in the context of geometric matching tasks. Further, we propose to use activation maps at different layers of a CNN, as an effective and principled replacement for the multi-resolution image pyramids often used for matching tasks. We propose concrete CNN architectures employing these ideas, and evaluate them on multiple datasets for 2D and 3D geometric matching as well as optical flow, demonstrating state-of-the-art results and generalization across datasets.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191