Hosein Hasanbeig, N. Jeppu, Alessandro Abate, Tom Melham, Daniel Kroening
This paper proposes DeepSynth, a method for effective training of deep reinforcement learning agents when the reward is sparse or non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorithm for synthesis of compact finite state automata to uncover this sequential structure automatically. We synthesise a human-interpretable automaton from trace data collected by exploring the environment. The state space of the environment is then enriched with the synthesised automaton, so that the generation of a control policy by deep reinforcement learning is guided by the discovered structure encoded in the automaton. The proposed approach is able to cope with both high-dimensional, low-level features and unknown sparse or non-Markovian rewards. We have evaluated DeepSynth’s performance in a set of experiments that includes the Atari game Montezuma’s Revenge, known to be challenging. Compared to approaches that rely solely on deep reinforcement learning, we obtain a reduction of two orders of magnitude in the iterations required for policy synthesis, and a significant improvement in scalability.
{"title":"Symbolic Task Inference in Deep Reinforcement Learning","authors":"Hosein Hasanbeig, N. Jeppu, Alessandro Abate, Tom Melham, Daniel Kroening","doi":"10.1613/jair.1.14063","DOIUrl":"https://doi.org/10.1613/jair.1.14063","url":null,"abstract":"This paper proposes DeepSynth, a method for effective training of deep reinforcement learning agents when the reward is sparse or non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorithm for synthesis of compact finite state automata to uncover this sequential structure automatically. We synthesise a human-interpretable automaton from trace data collected by exploring the environment. The state space of the environment is then enriched with the synthesised automaton, so that the generation of a control policy by deep reinforcement learning is guided by the discovered structure encoded in the automaton. The proposed approach is able to cope with both high-dimensional, low-level features and unknown sparse or non-Markovian rewards. We have evaluated DeepSynth’s performance in a set of experiments that includes the Atari game Montezuma’s Revenge, known to be challenging. Compared to approaches that rely solely on deep reinforcement learning, we obtain a reduction of two orders of magnitude in the iterations required for policy synthesis, and a significant improvement in scalability.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141812026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper contributes to the development of theoretical foundations of answer set programming. Groundbreaking work on the SM operator by Ferraris, Lee, and Lifschitz proposed a definition/semantics for logic (answer set) programs based on a syntactic transformation similar to parallel circumscription. That definition radically differed from its predecessors by using classical (second-order) logic and avoiding reference to either grounding or fixpoints. Yet, the work lacked the formalization of crucial and commonly used answer set programming language constructs called aggregates. In this paper, we present a characterization of logic programs with aggregates based on a many-sorted generalization of the SM operator. This characterization introduces new function symbols for aggregate operations and aggregate elements, whose meaning can be fixed by adding appropriate axioms to the result of the SM transformation. We prove that our characterization coincides with the ASP-Core-2 semantics for logic programs and, if we allow non-positive recursion through aggregates, it coincides with the semantics of the answer set solver CLINGO.
本文对答案集编程理论基础的发展做出了贡献。Ferraris、Lee 和 Lifschitz 关于 SM 算子的开创性工作提出了逻辑（答案集）程序的定义/语义学，其基础是类似于并行周延的语法转换。该定义使用经典（二阶）逻辑，避免了对接地或固定点的引用，与前人的定义截然不同。然而，这项工作缺乏对关键且常用的答案集编程语言构造（称为聚合）的形式化。在本文中，我们基于 SM 算子的多排序广义化，提出了具有聚合的逻辑程序的表征。该表征为聚合运算和聚合元素引入了新的函数符号，通过为 SM 变换的结果添加适当的公理，可以固定其含义。我们证明，我们的表征与逻辑程序的 ASP-Core-2 语义相吻合，而且，如果我们允许通过聚合进行非正递归，它还与答案集求解器 CLINGO 的语义相吻合。
{"title":"Axiomatization of Non-Recursive Aggregates in First-Order Answer Set Programming","authors":"Jorge Fandinno, Zachary Hansen, Yuliya Lierler","doi":"10.1613/jair.1.15786","DOIUrl":"https://doi.org/10.1613/jair.1.15786","url":null,"abstract":"This paper contributes to the development of theoretical foundations of answer set programming. Groundbreaking work on the SM operator by Ferraris, Lee, and Lifschitz proposed a definition/semantics for logic (answer set) programs based on a syntactic transformation similar to parallel circumscription. That definition radically differed from its predecessors by using classical (second-order) logic and avoiding reference to either grounding or fixpoints. Yet, the work lacked the formalization of crucial and commonly used answer set programming language constructs called aggregates. In this paper, we present a characterization of logic programs with aggregates based on a many-sorted generalization of the SM operator. This characterization introduces new function symbols for aggregate operations and aggregate elements, whose meaning can be fixed by adding appropriate axioms to the result of the SM transformation. We prove that our characterization coincides with the ASP-Core-2 semantics for logic programs and, if we allow non-positive recursion through aggregates, it coincides with the semantics of the answer set solver CLINGO.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141670554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maximum satisfiability (MaxSAT), employing propositional logic as the declarative language of choice, has turned into a viable approach to solving NP-hard optimization problems arising from artificial intelligence and other real-world settings. A key contributing factor to the success of MaxSAT is the rise of increasingly effective exact solvers that are based on iterative calls to a Boolean satisfiability (SAT) solver. The three types of SAT-based MaxSAT solving approaches, each with its distinguishing features, implemented in current state-of-the-art MaxSAT solvers are the core-guided, the implicit hitting set (IHS), and the objective-bounding approaches. The objective-bounding approach is based on directly searching over the objective function range by iteratively querying a SAT solver if the MaxSAT instance at hand has a solution under different bounds on the objective. In contrast, both core-guided and IHS are so-called unsatisfiability-based approaches that employ a SAT solver as an unsatisfiable core extractor to determine sources of inconsistencies, but critically differ in how the found unsatisfiable cores are made use of towards finding a provably optimal solution. Furthermore, a variety of different algorithmic variants of the core-guided approach in particular have been proposed and implemented in solvers. It is well-acknowledged that each of the three approaches has its advantages and disadvantages, which is also witnessed by instance and problem-domain specific runtime performance differences (and at times similarities) of MaxSAT solvers implementing variants of the approaches. However, the questions of to what extent the approaches are fundamentally different and how the benefits of the individual methods could be combined in a single algorithmic approach are currently not fully understood. In this work, we approach these questions by developing UniMaxSAT, a general unifying algorithmic framework. Based on the recent notion of abstract cores, UniMaxSAT captures in general core-guided, IHS and objective-bounding computations. The framework offers a unified way of establishing quite generally the correctness of the current approaches. We illustrate this by formally showing that UniMaxSAT can simulate the computations of various algorithmic instantiations of the three types of MaxSAT solving approaches. Furthermore, UniMaxSAT can be instantiated in novel ways giving rise to new algorithmic variants of the approaches. We illustrate this aspect by developing a prototype implementation of an algorithmic variant for MaxSAT based on the framework.
{"title":"Unifying SAT-Based Approaches to Maximum Satisfiability Solving","authors":"Hannes Ihalainen, Jeremias Berg, Matti Järvisalo","doi":"10.1613/jair.1.15986","DOIUrl":"https://doi.org/10.1613/jair.1.15986","url":null,"abstract":"Maximum satisfiability (MaxSAT), employing propositional logic as the declarative language of choice, has turned into a viable approach to solving NP-hard optimization problems arising from artificial intelligence and other real-world settings. A key contributing factor to the success of MaxSAT is the rise of increasingly effective exact solvers that are based on iterative calls to a Boolean satisfiability (SAT) solver. The three types of SAT-based MaxSAT solving approaches, each with its distinguishing features, implemented in current state-of-the-art MaxSAT solvers are the core-guided, the implicit hitting set (IHS), and the objective-bounding approaches. The objective-bounding approach is based on directly searching over the objective function range by iteratively querying a SAT solver if the MaxSAT instance at hand has a solution under different bounds on the objective. In contrast, both core-guided and IHS are so-called unsatisfiability-based approaches that employ a SAT solver as an unsatisfiable core extractor to determine sources of inconsistencies, but critically differ in how the found unsatisfiable cores are made use of towards finding a provably optimal solution. Furthermore, a variety of different algorithmic variants of the core-guided approach in particular have been proposed and implemented in solvers. It is well-acknowledged that each of the three approaches has its advantages and disadvantages, which is also witnessed by instance and problem-domain specific runtime performance differences (and at times similarities) of MaxSAT solvers implementing variants of the approaches. However, the questions of to what extent the approaches are fundamentally different and how the benefits of the individual methods could be combined in a single algorithmic approach are currently not fully understood. In this work, we approach these questions by developing UniMaxSAT, a general unifying algorithmic framework. Based on the recent notion of abstract cores, UniMaxSAT captures in general core-guided, IHS and objective-bounding computations. The framework offers a unified way of establishing quite generally the correctness of the current approaches. We illustrate this by formally showing that UniMaxSAT can simulate the computations of various algorithmic instantiations of the three types of MaxSAT solving approaches. Furthermore, UniMaxSAT can be instantiated in novel ways giving rise to new algorithmic variants of the approaches. We illustrate this aspect by developing a prototype implementation of an algorithmic variant for MaxSAT based on the framework.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141671335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present an approach for translating Totally Ordered Hierarchical Task Network (HTN) planning problems to classical planning problems. While this enables the use of sophisticated classical planning systems to find solutions, we need to overcome the differences in expressiveness of these two planning formalisms. Prior work on this topic did this by translating bounded HTN problems. In contrast, we approximate them, i.e., we change the problem such that every action sequence that is a solution to the HTN problem is also a solution for the classical problem, but the latter might have more solutions. To obtain a sound overall approach, we verify solutions returned by the classical planning system to ensure that they are also solutions to the HTN problem. For translation and approximation, we use techniques introduced to approximate Context-Free Languages by using Finite Automata. We named our system Toad (Totally Ordered HTN Approximation using DFA). For a subset of HTN problems the translation is even possible without approximation. Whether or not it is necessary is decided based on the property of self-embedding, which comes also from the field of formal languages. We investigate the theoretical connection of self-embedding and tail-recursiveness, a property from the HTN literature used to identify a subclass of HTN planning problems that can be translated to classical planning, and show that it is more general. To guide the classical planner, we introduce a novel heuristic tailored towards our models. We evaluate Toad on the benchmark set of the 2020 International Planning Competition. Our evaluation shows that (1) most problems can be translated without approximation and that (2) Toad is competitive with the state of the art in HTN planning.
{"title":"The TOAD System for Totally Ordered HTN Planning","authors":"Daniel Höller","doi":"10.1613/jair.1.14945","DOIUrl":"https://doi.org/10.1613/jair.1.14945","url":null,"abstract":"We present an approach for translating Totally Ordered Hierarchical Task Network (HTN) planning problems to classical planning problems. While this enables the use of sophisticated classical planning systems to find solutions, we need to overcome the differences in expressiveness of these two planning formalisms. Prior work on this topic did this by translating bounded HTN problems. In contrast, we approximate them, i.e., we change the problem such that every action sequence that is a solution to the HTN problem is also a solution for the classical problem, but the latter might have more solutions. To obtain a sound overall approach, we verify solutions returned by the classical planning system to ensure that they are also solutions to the HTN problem.\u0000For translation and approximation, we use techniques introduced to approximate Context-Free Languages by using Finite Automata. We named our system Toad (Totally Ordered HTN Approximation using DFA). For a subset of HTN problems the translation is even possible without approximation. Whether or not it is necessary is decided based on the property of self-embedding, which comes also from the field of formal languages. We investigate the theoretical connection of self-embedding and tail-recursiveness, a property from the HTN literature used to identify a subclass of HTN planning problems that can be translated to classical planning, and show that it is more general. To guide the classical planner, we introduce a novel heuristic tailored towards our models.\u0000We evaluate Toad on the benchmark set of the 2020 International Planning Competition. Our evaluation shows that (1) most problems can be translated without approximation and that (2) Toad is competitive with the state of the art in HTN planning.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141347313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farzane Aminmansour, Taher Jafferjee, Ehsan Imani, Erin J. Talvitie, Michael Bowling, Martha White
Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environment model. However, it is often difficult to learn accurate models of environment dynamics, and even small errors may result in failure of Dyna agents. In this paper, we highlight that one potential cause of that failure is bootstrapping off of the values of simulated states, and introduce a new Dyna algorithm to avoid this failure. We discuss a design space of Dyna algorithms, based on using successor or predecessor models---simulating forwards or backwards---and using one-step or multi-step updates. Three of the variants have been explored, but surprisingly the fourth variant has not: using predecessor models with multi-step updates. We present the emph{Hallucinated Value Hypothesis} (HVH): updating the values of real states towards values of simulated states can result in misleading action values which adversely affect the control policy. We discuss and evaluate all four variants of Dyna amongst which three update real states toward simulated states --- so potentially toward hallucinated values --- and our proposed approach, which does not. The experimental results provide evidence for the HVH, and suggest that using predecessor models with multi-step updates is a fruitful direction toward developing Dyna algorithms that are more robust to model error.
{"title":"Mitigating Value Hallucination in Dyna-Style Planning via Multistep Predecessor Models","authors":"Farzane Aminmansour, Taher Jafferjee, Ehsan Imani, Erin J. Talvitie, Michael Bowling, Martha White","doi":"10.1613/jair.1.15155","DOIUrl":"https://doi.org/10.1613/jair.1.15155","url":null,"abstract":"Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environment model. However, it is often difficult to learn accurate models of environment dynamics, and even small errors may result in failure of Dyna agents. In this paper, we highlight that one potential cause of that failure is bootstrapping off of the values of simulated states, and introduce a new Dyna algorithm to avoid this failure. We discuss a design space of Dyna algorithms, based on using successor or predecessor models---simulating forwards or backwards---and using one-step or multi-step updates. Three of the variants have been explored, but surprisingly the fourth variant has not: using predecessor models with multi-step updates. We present the emph{Hallucinated Value Hypothesis} (HVH): updating the values of real states towards values of simulated states can result in misleading action values which adversely affect the control policy. We discuss and evaluate all four variants of Dyna amongst which three update real states toward simulated states --- so potentially toward hallucinated values --- and our proposed approach, which does not. The experimental results provide evidence for the HVH, and suggest that using predecessor models with multi-step updates is a fruitful direction toward developing Dyna algorithms that are more robust to model error.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141368219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Actions in most real-world continuous domains cannot be executed exactly. An agent’s performance in these domains is influenced by two critical factors: the ability to select effective actions (decision-making skill), and how precisely it can execute those selected actions (execution skill). This article addresses the problem of estimating the execution and decision-making skill of an agent, given observations. Several execution skill estimation methods are presented, each of which utilize different information from the observations and make assumptions about the agent’s decision-making ability. A final novel method forgoes these assumptions about decision-making and instead estimates the execution and decision-making skills simultaneously under a single Bayesian framework. Experimental results in several domains evaluate the estimation accuracy of the estimators, especially focusing on how robust they are as agents and their decision-making methods are varied. These results demonstrate that reasoning about both types of skill together significantly improves the robustness and accuracy of execution skill estimation. A case study is presented using the proposed methods to estimate the skill of Major League Baseball pitchers, demonstrating how these methods can be applied to real-world data sources.
{"title":"Estimating Agent Skill in Continuous Action Domains","authors":"Christopher Archibald, Delma Nieves-Rivera","doi":"10.1613/jair.1.15326","DOIUrl":"https://doi.org/10.1613/jair.1.15326","url":null,"abstract":"Actions in most real-world continuous domains cannot be executed exactly. An agent’s performance in these domains is influenced by two critical factors: the ability to select effective actions (decision-making skill), and how precisely it can execute those selected actions (execution skill). This article addresses the problem of estimating the execution and decision-making skill of an agent, given observations. Several execution skill estimation methods are presented, each of which utilize different information from the observations and make assumptions about the agent’s decision-making ability. A final novel method forgoes these assumptions about decision-making and instead estimates the execution and decision-making skills simultaneously under a single Bayesian framework. Experimental results in several domains evaluate the estimation accuracy of the estimators, especially focusing on how robust they are as agents and their decision-making methods are varied. These results demonstrate that reasoning about both types of skill together significantly improves the robustness and accuracy of execution skill estimation. A case study is presented using the proposed methods to estimate the skill of Major League Baseball pitchers, demonstrating how these methods can be applied to real-world data sources.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140990329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Learning from imperfect demonstrations is a crucial challenge in imitation learning (IL). Unlike existing works that still rely on the enormous effort of expert demonstrators, we consider a more cost-effective option for obtaining a large number of demonstrations. That is, hire annotators to label actions for existing image records in realistic scenarios. However, action noise can occur when annotators are not domain experts or encounter confusing states. In this work, we introduce two particular forms of action noise, i.e., state-independent and state-dependent action noise. Previous IL methods fail to achieve expert-level performance when the demonstrations contain action noise, especially the state-dependent action noise. To mitigate the harmful effects of action noises, we propose a robust learning paradigm called USN (Uncertainty-aware Sample-selection with Negative learning). The model first estimates the predictive uncertainty for all demonstration data and then selects sampleswith high loss based on the uncertainty measures. Finally, it updates the model parameters with additional negative learning on the selected samples. Empirical results in Box2D tasks and Atari games show that USN consistently improves the final rewards of behavioral cloning, online imitation learning, and offline imitation learning methods under various action noises. The ratio of significant improvements is up to 94.44%. Moreover, our method scales to conditional imitation learning with real-world noisy commands in urban driving
{"title":"USN: A Robust Imitation Learning Method against Diverse Action Noise","authors":"Xingrui Yu, Bo Han, I. Tsang","doi":"10.1613/jair.1.15819","DOIUrl":"https://doi.org/10.1613/jair.1.15819","url":null,"abstract":"Learning from imperfect demonstrations is a crucial challenge in imitation learning (IL). Unlike existing works that still rely on the enormous effort of expert demonstrators, we consider a more cost-effective option for obtaining a large number of demonstrations. That is, hire annotators to label actions for existing image records in realistic scenarios. However, action noise can occur when annotators are not domain experts or encounter confusing states. In this work, we introduce two particular forms of action noise, i.e., state-independent and state-dependent action noise. Previous IL methods fail to achieve expert-level performance when the demonstrations contain action noise, especially the state-dependent action noise. To mitigate the harmful effects of action noises, we propose a robust learning paradigm called USN (Uncertainty-aware Sample-selection with Negative learning). The model first estimates the predictive uncertainty for all demonstration data and then selects sampleswith high loss based on the uncertainty measures. Finally, it updates the model parameters with additional negative learning on the selected samples. Empirical results in Box2D tasks and Atari games show that USN consistently improves the final rewards of behavioral cloning, online imitation learning, and offline imitation learning methods under various action noises. The ratio of significant improvements is up to 94.44%. Moreover, our method scales to conditional imitation learning with real-world noisy commands in urban driving","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140678351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Focusing on Stable Roommates (SR), we contribute to the toolbox for conducting experiments for stable matching problems. We introduce the polynomial-time computable mutual attraction distance to measure the similarity of SR instances, analyze its properties, and use it to create a map of SR instances. This map visualizes 460 synthetic SR instances (each sampled from one of ten different statistical cultures) as follows: Each instance is a point in the plane, and two points are close on the map if the corresponding SR instances are similar with respect to our mutual attraction distance to each other. Subsequently, we conduct several illustrative experiments and depict their results on the map, illustrating the map’s usefulness as a non-aggregate visualization tool, the diversity of our generated dataset, and the need to use instances sampled from different statistical cultures. Lastly, we extend our approach to the bipartite Stable Marriage problem.
以稳定室友（SR）为重点，我们为开展稳定匹配问题实验的工具箱做出了贡献。我们引入了多项式时间可计算的相互吸引距离来测量 SR 实例的相似性，分析了它的特性，并用它创建了 SR 实例的地图。该地图将 460 个合成 SR 实例（每个实例从十种不同的统计文化中抽取一个）可视化如下：每个实例都是平面上的一个点，如果对应的 SR 实例在相互吸引距离上相似，则地图上的两个点就接近。随后，我们进行了几个说明性实验，并在地图上描绘了实验结果，说明了地图作为非聚合可视化工具的实用性、我们生成的数据集的多样性以及使用从不同统计文化中采样的实例的必要性。最后，我们将我们的方法扩展到了两方稳定婚姻问题。
{"title":"A Map of Diverse Synthetic Stable Matching Instances","authors":"Niclas Boehmer, Klaus Heeger, Stanislaw Szufa","doi":"10.1613/jair.1.15213","DOIUrl":"https://doi.org/10.1613/jair.1.15213","url":null,"abstract":"Focusing on Stable Roommates (SR), we contribute to the toolbox for conducting experiments for stable matching problems. We introduce the polynomial-time computable mutual attraction distance to measure the similarity of SR instances, analyze its properties, and use it to create a map of SR instances. This map visualizes 460 synthetic SR instances (each sampled from one of ten different statistical cultures) as follows: Each instance is a point in the plane, and two points are close on the map if the corresponding SR instances are similar with respect to our mutual attraction distance to each other. Subsequently, we conduct several illustrative experiments and depict their results on the map, illustrating the map’s usefulness as a non-aggregate visualization tool, the diversity of our generated dataset, and the need to use instances sampled from different statistical cultures. Lastly, we extend our approach to the bipartite Stable Marriage problem.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140746025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a Dynamic Interaction Graph Convolutional Network (DIGCN), an image object detection method based on learnable proposals and GCN. Existing object detection methods usually work on dense candidates, resulting in redundant and near-duplicate results. Meanwhile, non-maximum suppression post-processing operations are required to eliminate negative effects, which increases the computational complexity. Although the existing sparse detector avoids cumbersome post-processing operations, it ignores the potential relationship between objects and proposals, which hinders detection accuracy improvement. Therefore, we propose a dynamic interaction GCN module in the DIGCN, which performs dynamic interaction and relational modeling on the proposal boxes and proposal features to improve the object detection accuracy. In addition, we introduce a learnable proposal method with a sparse set of learned object proposals to eliminate a huge number of hand-designed object candidates, avoiding complicated tasks such as object candidate design and many-to-one label assignment, and reducing object detection model complexity to a certain extent. DIGCN demonstrates accuracy and run-time performance on par with the well-established and highly optimized detector baselines on the challenging COCO dataset, e.g. with the ResNet-101FPN as the backbone our method attains the accuracy of 46.5 AP while processing 13 frames per second. Our work provides a new method for object detection research.
{"title":"DIGCN: A Dynamic Interaction Graph Convolutional Network Based on Learnable Proposals for Object Detection","authors":"Pingping Cao, Yanping Zhu, Yuhao Jin, Benkun Ruan, Qiang Niu","doi":"10.1613/jair.1.15698","DOIUrl":"https://doi.org/10.1613/jair.1.15698","url":null,"abstract":"We propose a Dynamic Interaction Graph Convolutional Network (DIGCN), an image object detection method based on learnable proposals and GCN. Existing object detection methods usually work on dense candidates, resulting in redundant and near-duplicate results. Meanwhile, non-maximum suppression post-processing operations are required to eliminate negative effects, which increases the computational complexity. Although the existing sparse detector avoids cumbersome post-processing operations, it ignores the potential relationship between objects and proposals, which hinders detection accuracy improvement. Therefore, we propose a dynamic interaction GCN module in the DIGCN, which performs dynamic interaction and relational modeling on the proposal boxes and proposal features to improve the object detection accuracy. In addition, we introduce a learnable proposal method with a sparse set of learned object proposals to eliminate a huge number of hand-designed object candidates, avoiding complicated tasks such as object candidate design and many-to-one label assignment, and reducing object detection model complexity to a certain extent. DIGCN demonstrates accuracy and run-time performance on par with the well-established and highly optimized detector baselines on the challenging COCO dataset, e.g. with the ResNet-101FPN as the backbone our method attains the accuracy of 46.5 AP while processing 13 frames per second. Our work provides a new method for object detection research.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140741593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shaheen Fatima, Nicholas R. Jennings, Michael Wooldridge
Social dilemmas are situations of inter-dependent decision making in which individual rationality can lead to outcomes with poor social qualities. The ubiquity of social dilemmas in social, biological, and computational systems has generated substantial research across these diverse disciplines into the study of mechanisms for avoiding deficient outcomes by promoting and maintaining mutual cooperation. Much of this research is focused on studying how individuals faced with a dilemma can learn to cooperate by adapting their behaviours according to their past experience. In particular, three types of learning approaches have been studied: evolutionary game-theoretic learning, reinforcement learning, and best-response learning. This article is a comprehensive integrated survey of these learning approaches in the context of dilemma games. We formally introduce dilemma games and their inherent challenges. We then outline the three learning approaches and, for each approach, provide a survey of the solutions proposed for dilemma resolution. Finally, we provide a comparative summary and discuss directions in which further research is needed.
{"title":"Learning to Resolve Social Dilemmas: A Survey","authors":"Shaheen Fatima, Nicholas R. Jennings, Michael Wooldridge","doi":"10.1613/jair.1.15167","DOIUrl":"https://doi.org/10.1613/jair.1.15167","url":null,"abstract":"Social dilemmas are situations of inter-dependent decision making in which individual rationality can lead to outcomes with poor social qualities. The ubiquity of social dilemmas in social, biological, and computational systems has generated substantial research across these diverse disciplines into the study of mechanisms for avoiding deficient outcomes by promoting and maintaining mutual cooperation. Much of this research is focused on studying how individuals faced with a dilemma can learn to cooperate by adapting their behaviours according to their past experience. In particular, three types of learning approaches have been studied: evolutionary game-theoretic learning, reinforcement learning, and best-response learning. This article is a comprehensive integrated survey of these learning approaches in the context of dilemma games. We formally introduce dilemma games and their inherent challenges. We then outline the three learning approaches and, for each approach, provide a survey of the solutions proposed for dilemma resolution. Finally, we provide a comparative summary and discuss directions in which further research is needed.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140246182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：