A moral planning agent (MPA) seeks to compare two plans or compute an optimal plan in an interactive setting with other agents, where relative ideality and optimality of plans are defined with respect to a prioritized value base. We model MPAs whose values are expressed by formulas of linear temporal logic (LTL) and define comparison for both joint plans and individual plans. We introduce different evaluation criteria for individual plans including an optimistic (risk-seeking) criterion, a pessimistic (risk-averse) one, and two criteria based on the use of anticipated responsibility. We provide complexity results for a variety of MPA problems.
{"title":"Moral Planning Agents with LTL Values","authors":"Umberto Grandi, E. Lorini, Timothy Parker","doi":"10.24963/ijcai.2023/47","DOIUrl":"https://doi.org/10.24963/ijcai.2023/47","url":null,"abstract":"A moral planning agent (MPA) seeks to compare two plans or compute an optimal plan in an interactive setting with other agents, where relative ideality and optimality of plans are defined with respect to a prioritized value base. We model MPAs whose values are expressed by formulas of linear temporal logic (LTL) and define comparison for both joint plans and individual plans. We introduce different evaluation criteria for individual plans including an optimistic (risk-seeking) criterion, a pessimistic (risk-averse) one, and two criteria based on the use of anticipated responsibility. We provide complexity results for a variety of MPA problems.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115051465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, techniques utilizing frequency-based methods have gained significant attention, as they exhibit exceptional restoration capabilities for detail and structure in video super-resolution tasks. However, most of these frequency-based methods mainly have three major limitations: 1) insufficient exploration of object motion information, 2) inadequate enhancement for high-fidelity regions, and 3) loss of spatial information during convolution. In this paper, we propose a novel network, Directional Frequency Video Super-Resolution (DFVSR), to address these limitations. Specifically, we reconsider object motion from a new perspective and propose Directional Frequency Representation (DFR), which not only borrows the property of frequency representation of detail and structure information but also contains the direction information of the object motion that is extremely significant in videos. Based on this representation, we propose a Directional Frequency-Enhanced Alignment (DFEA) to use double enhancements of task-related information for ensuring the retention of high-fidelity frequency regions to generate the high-quality alignment feature. Furthermore, we design a novel Asymmetrical U-shaped network architecture to progressively fuse these alignment features and output the final output. This architecture enables the intercommunication of the same level of resolution in the encoder and decoder to achieve the supplement of spatial information. Powered by the above designs, our method achieves superior performance over state-of-the-art models on both quantitative and qualitative evaluations.
最近，利用基于频率的方法的技术获得了极大的关注，因为它们在视频超分辨率任务中表现出对细节和结构的卓越恢复能力。然而，这些基于频率的方法大多存在三个主要的局限性:1)对目标运动信息的挖掘不足;2)对高保真区域的增强不足;3)卷积过程中空间信息的丢失。在本文中，我们提出了一种新的网络，定向频率视频超分辨率(DFVSR)，以解决这些限制。具体来说，我们从一个新的角度重新考虑物体的运动，提出了方向频率表示(Directional Frequency Representation, DFR)，它不仅借用了细节和结构信息的频率表示特性，而且还包含了在视频中非常重要的物体运动的方向信息。在此基础上，我们提出了一种定向频率增强对准(DFEA)，利用任务相关信息的双重增强来确保高保真频率区域的保留，从而产生高质量的对准特征。此外，我们设计了一种新颖的非对称u型网络架构，以逐步融合这些对齐特征并输出最终输出。这种结构使得编码器和解码器在相同分辨率的情况下相互通信，从而实现空间信息的补充。在上述设计的支持下，我们的方法在定量和定性评估方面都优于最先进的模型。
{"title":"DFVSR: Directional Frequency Video Super-Resolution via Asymmetric and Enhancement Alignment Network","authors":"Shuting Dong, Feng Lu, Zhe Wu, Chun Yuan","doi":"10.24963/ijcai.2023/76","DOIUrl":"https://doi.org/10.24963/ijcai.2023/76","url":null,"abstract":"Recently, techniques utilizing frequency-based methods have gained significant attention, as they exhibit exceptional restoration capabilities for detail and structure in video super-resolution tasks. However, most of these frequency-based methods mainly have three major limitations: 1) insufficient exploration of object motion information, 2) inadequate enhancement for high-fidelity regions, and 3) loss of spatial information during convolution. In this paper, we propose a novel network, Directional Frequency Video Super-Resolution (DFVSR), to address these limitations. Specifically, we reconsider object motion from a new perspective and propose Directional Frequency Representation (DFR), which not only borrows the property of frequency representation of detail and structure information but also contains the direction information of the object motion that is extremely significant in videos. Based on this representation, we propose a Directional Frequency-Enhanced Alignment (DFEA) to use double enhancements of task-related information for ensuring the retention of high-fidelity frequency regions to generate the high-quality alignment feature. Furthermore, we design a novel Asymmetrical U-shaped network architecture to progressively fuse these alignment features and output the final output. This architecture enables the intercommunication of the same level of resolution in the encoder and decoder to achieve the supplement of spatial information. Powered by the above designs, our method achieves superior performance over state-of-the-art models on both quantitative and qualitative evaluations.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115249546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Harsha Kokel, Junkyu Lee, Michael Katz, Shirin Sohrabi, Kavitha Srinivas
Planning tasks succinctly represent labeled transition systems, with each ground action corresponding to a label. This granularity, however, is not necessary for solving planning tasks and can be harmful, especially for model-free methods. In order to apply such methods, the label sets are often manually reduced. In this work, we propose automating this manual process. We characterize a valid label reduction for classical planning tasks and propose an automated way of obtaining such valid reductions by leveraging lifted mutex groups. Our experiments show a significant reduction in the action label space size across a wide collection of planning domains. We demonstrate the benefit of our automated label reduction in two separate use cases: improved sample complexity of model-free reinforcement learning algorithms and speeding up successor generation in lifted planning. The code and supplementary material are available at https://github.com/IBM/Parameter-Seed-Set.
{"title":"Action Space Reduction for Planning Domains","authors":"Harsha Kokel, Junkyu Lee, Michael Katz, Shirin Sohrabi, Kavitha Srinivas","doi":"10.24963/ijcai.2023/599","DOIUrl":"https://doi.org/10.24963/ijcai.2023/599","url":null,"abstract":"Planning tasks succinctly represent labeled transition systems, with each ground action corresponding to a label. This granularity, however, is not necessary for solving planning tasks and can be harmful, especially for model-free methods. In order to apply such methods, the label sets are often manually reduced. In this work, we propose automating this manual process. We characterize a valid label reduction for classical planning tasks and propose an automated way of obtaining such valid reductions by leveraging lifted mutex groups. Our experiments show a significant reduction in the action label space size across a wide collection of planning domains. We demonstrate the benefit of our automated label reduction in two separate use cases: improved sample complexity of model-free reinforcement learning algorithms and speeding up successor generation in lifted planning. The code and supplementary material are available at https://github.com/IBM/Parameter-Seed-Set.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115487729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jianping Zhang, Yung-Chieh Huang, Weibin Wu, Michael R. Lyu
Language models are known to be vulnerable to textual adversarial attacks, which add human-imperceptible perturbations to the input to mislead DNNs. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs before real-world deployment. However, existing word-level attacks have two major deficiencies: (1) They may change the semantics of the original sentence. (2) The generated adversarial sample can appear unnatural to humans due to the introduction of out-of-domain substitute words. In this paper, to address such drawbacks, we propose a semantics- and domain-aware word-level attack method. Specifically, we greedily replace the important words in a sentence with the ones suggested by a language model. The language model is trained to be semantics- and domain-aware via contrastive learning and in-domain pre-training. Furthermore, to balance the quality of adversarial examples and the attack success rate, we propose an iterative updating framework to optimize the contrastive learning loss and the in-domain pre-training loss in circular order. Comprehensive experimental comparisons confirm the superiority of our approach. Notably, compared with state-of-the-art benchmarks, our strategy can achieve over 3% improvement in attack success rates and 9.8% improvement in the quality of adversarial examples.
{"title":"Towards Semantics- and Domain-Aware Adversarial Attacks","authors":"Jianping Zhang, Yung-Chieh Huang, Weibin Wu, Michael R. Lyu","doi":"10.24963/ijcai.2023/60","DOIUrl":"https://doi.org/10.24963/ijcai.2023/60","url":null,"abstract":"Language models are known to be vulnerable to textual adversarial attacks, which add human-imperceptible perturbations to the input to mislead DNNs. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs before real-world deployment. However, existing word-level attacks have two major deficiencies: (1) They may change the semantics of the original sentence. (2) The generated adversarial sample can appear unnatural to humans due to the introduction of out-of-domain substitute words. In this paper, to address such drawbacks, we propose a semantics- and domain-aware word-level attack method. Specifically, we greedily replace the important words in a sentence with the ones suggested by a language model. The language model is trained to be semantics- and domain-aware via contrastive learning and in-domain pre-training. Furthermore, to balance the quality of adversarial examples and the attack success rate, we propose an iterative updating framework to optimize the contrastive learning loss and the in-domain pre-training loss in circular order. Comprehensive experimental comparisons confirm the superiority of our approach. Notably, compared with state-of-the-art benchmarks, our strategy can achieve over 3% improvement in attack success rates and 9.8% improvement in the quality of adversarial examples.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"271 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116422536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes two Unsupervised constituent Parsing models (UPOA and UPIO) that calculate inside and outside association scores solely based on the self-attention weight matrix learned in a pretrained language model. The proposed unsupervised parsing models are further extended to few-shot parsing models (FPOA, FPIO) that use a few annotated trees to fine-tune the linear projection matrices in self-attention. Experiments on PTB and SPRML show that both unsupervised and few-shot parsing methods are better than or comparable to the previous methods.
{"title":"Unsupervised and Few-Shot Parsing from Pretrained Language Models (Extended Abstract)","authors":"Zhiyuan Zeng, Deyi Xiong","doi":"10.24963/ijcai.2023/797","DOIUrl":"https://doi.org/10.24963/ijcai.2023/797","url":null,"abstract":"This paper proposes two Unsupervised constituent Parsing models (UPOA and UPIO) that calculate inside and outside association scores solely based on the self-attention weight matrix learned in a pretrained language model. The proposed unsupervised parsing models are further extended to few-shot parsing models (FPOA, FPIO) that use a few annotated trees to fine-tune the linear projection matrices in self-attention. Experiments on PTB and SPRML show that both unsupervised and few-shot parsing methods are better than or comparable to the previous methods.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122416851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Acoustic non-line-of-sight (NLOS) imaging aims to reconstruct hidden scenes by analyzing reflections of acoustic waves. Despite recent developments in the field, existing methods still have limitations such as sensitivity to noise in a physical model and difficulty in reconstructing unseen objects in a deep learning model. To address these limitations, we propose a novel cross-modal knowledge distillation (CMKD) approach for acoustic NLOS imaging. Our method transfers knowledge from a well-trained image network to an audio network, effectively combining the strengths of both modalities. As a result, it is robust to noise and superior in reconstructing unseen objects. Additionally, we evaluate real-world datasets and demonstrate that the proposed method outperforms state-of-the-art methods in acoustic NLOS imaging. The experimental results indicate that CMKD is an effective solution for addressing the limitations of current acoustic NLOS imaging methods. Our code, model, and data are available at https://github.com/shineh96/Acoustic-NLOS-CMKD.
{"title":"Acoustic NLOS Imaging with Cross Modal Knowledge Distillation","authors":"Ui-Hyeon Shin, Seungwoo Jang, Kwangsu Kim","doi":"10.24963/ijcai.2023/156","DOIUrl":"https://doi.org/10.24963/ijcai.2023/156","url":null,"abstract":"Acoustic non-line-of-sight (NLOS) imaging aims to reconstruct hidden scenes by analyzing reflections of acoustic waves. Despite recent developments in the field, existing methods still have limitations such as sensitivity to noise in a physical model and difficulty in reconstructing unseen objects in a deep learning model. To address these limitations, we propose a novel cross-modal knowledge distillation (CMKD) approach for acoustic NLOS imaging. Our method transfers knowledge from a well-trained image network to an audio network, effectively combining the strengths of both modalities. As a result, it is robust to noise and superior in reconstructing unseen objects. Additionally, we evaluate real-world datasets and demonstrate that the proposed method outperforms state-of-the-art methods in acoustic NLOS imaging. The experimental results indicate that CMKD is an effective solution for addressing the limitations of current acoustic NLOS imaging methods. Our code, model, and data are available at https://github.com/shineh96/Acoustic-NLOS-CMKD.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"2 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114044493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial Intelligence often relies on information obtained from others through crowdsourcing, federated learning, or data markets. It is crucial to ensure that this data is accurate. Over the past 20 years, a variety of incentive mechanisms have been developed that use game theory to reward the accuracy of contributed data. These techniques are applicable to many settings where AI uses contributed data. This survey categorizes the different techniques and their properties, and shows their limits and tradeoffs. It identifies open issues and points to possible directions to address these.
{"title":"Game-theoretic Mechanisms for Eliciting Accurate Information","authors":"B. Faltings","doi":"10.24963/ijcai.2023/740","DOIUrl":"https://doi.org/10.24963/ijcai.2023/740","url":null,"abstract":"Artificial Intelligence often relies on information obtained from others through crowdsourcing, federated learning, or data markets. It is crucial to ensure that this data is accurate. Over the past 20 years, a variety of incentive mechanisms have been developed that use game theory to reward the accuracy of contributed data. These techniques are applicable to many settings where AI uses contributed data.\u0000\u0000\u0000\u0000This survey categorizes the different techniques and their properties, and shows their limits and tradeoffs. It identifies open issues and points to possible directions to address these.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114124778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wen Wang, Hongyang Chen, Hong Yu, Xianchao Zhang
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial attacks, as it will directly affect the query efficiency. Recent works have attempted to utilize gradient priors to facilitate score-based methods to obtain better results. However, these gradient priors still suffer from the edge gradient discrepancy issue and the successive iteration gradient direction issue, thus are difficult to simply extend to decision-based methods. In this paper, we propose a novel Decision-based Black-box Attack framework with Gradient Priors (DBA-GP), which seamlessly integrates the data-dependent gradient prior and time-dependent prior into the gradient estimation procedure. First, by leveraging the joint bilateral filter to deal with each random perturbation, DBA-GP can guarantee that the generated perturbations in edge locations are hardly smoothed, i.e., alleviating the edge gradient discrepancy, thus remaining the characteristics of the original image as much as possible. Second, by utilizing a new gradient updating strategy to automatically adjust the successive iteration gradient direction, DBA-GP can accelerate the convergence speed, thus improving the query efficiency. Extensive experiments have demonstrated that the proposed method outperforms other strong baselines significantly.
{"title":"Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors","authors":"Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wen Wang, Hongyang Chen, Hong Yu, Xianchao Zhang","doi":"10.24963/ijcai.2023/133","DOIUrl":"https://doi.org/10.24963/ijcai.2023/133","url":null,"abstract":"Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial attacks, as it will directly affect the query efficiency. Recent works have attempted to utilize gradient priors to facilitate score-based methods to obtain better results. However, these gradient priors still suffer from the edge gradient discrepancy issue and the successive iteration gradient direction issue, thus are difficult to simply extend to decision-based methods. In this paper, we propose a novel Decision-based Black-box Attack framework with Gradient Priors (DBA-GP), which seamlessly integrates the data-dependent gradient prior and time-dependent prior into the gradient estimation procedure. First, by leveraging the joint bilateral filter to deal with each random perturbation, DBA-GP can guarantee that the generated perturbations in edge locations are hardly smoothed, i.e., alleviating the edge gradient discrepancy, thus remaining the characteristics of the original image as much as possible. Second, by utilizing a new gradient updating strategy to automatically adjust the successive iteration gradient direction, DBA-GP can accelerate the convergence speed, thus improving the query efficiency. Extensive experiments have demonstrated that the proposed method outperforms other strong baselines significantly.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122090117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qinqing Liu, Fei Dou, Meijian Yang, Ezana Amdework, Guiling Wang, J. Bi
Accurate prediction of crop yield under the conditions of climate change is crucial to ensure food security. Transformers have shown remarkable success in modeling sequential data and hold the potential for improving crop yield prediction. To understand how weather and meteorological sequence variables affect crop yield, the positional encoding used in Transformers is typically shared across different sample sequences. We argue that it is necessary and beneficial to differentiate the positional encoding for distinct samples based on time-invariant properties of the sequences. Particularly, the sequence variables influencing crop yield vary according to static variables such as geographical locations. Sample data from southern areas may benefit from more tailored positional encoding different from that for northern areas. We propose a novel transformer based architecture for accurate and robust crop yield prediction, by introducing a Customized Positional Encoding (CPE) that encodes a sequence adaptively according to static information associated with the sequence. Empirical studies demonstrate the effectiveness of the proposed novel architecture and show that partially lin- earized attention better captures the bias introduced by side information than softmax re-weighting. The resultant crop yield prediction model is robust to climate change, with mean-absolute-error reduced by up to 26% compared to the best baseline model in extreme drought years.
{"title":"Customized Positional Encoding to Combine Static and Time-varying Data in Robust Representation Learning for Crop Yield Prediction","authors":"Qinqing Liu, Fei Dou, Meijian Yang, Ezana Amdework, Guiling Wang, J. Bi","doi":"10.24963/ijcai.2023/676","DOIUrl":"https://doi.org/10.24963/ijcai.2023/676","url":null,"abstract":"Accurate prediction of crop yield under the conditions of climate change is crucial to ensure food security. Transformers have shown remarkable success in modeling sequential data and hold the potential for improving crop yield prediction. To understand how weather and meteorological sequence variables affect crop yield, the positional encoding used in Transformers is typically shared across different sample sequences. We argue that it is necessary and beneficial to differentiate the positional encoding for distinct samples based on time-invariant properties of the sequences. Particularly, the sequence variables influencing crop yield vary according to static variables such as geographical locations. Sample data from southern areas may benefit from more tailored positional encoding different from that for northern areas. We propose a novel transformer based architecture for accurate and robust crop yield prediction, by introducing a Customized Positional Encoding (CPE) that encodes a sequence adaptively according to static information associated with the sequence. Empirical studies demonstrate the effectiveness of the proposed novel architecture and show that partially lin-\u0000\u0000earized attention better captures the bias introduced by side information than softmax re-weighting. The resultant crop yield prediction model is robust to climate change, with mean-absolute-error reduced by up to 26% compared to the best baseline model in extreme drought years.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122106970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md Asifur Rahman, Tongtong Liu, Sarra M. Alqahtani
Learning by exploration makes reinforcement learning (RL) potentially attractive for many real-world applications. However, this learning process makes RL inherently too vulnerable to be used in real-world applications where safety is of utmost importance. Most prior studies consider exploration at odds with safety and thereby restrict it using either joint optimization of task and safety or imposing constraints for safe exploration. This paper migrates from the current convention to using exploration as a key to safety by learning safety as a robust behavior that completely excludes any behavioral pattern responsible for safety violations. Adversarial Behavior Exclusion for Safe RL (AdvEx-RL) learns a behavioral representation of the agent's safety violations by approximating an optimal adversary utilizing exploration and later uses this representation to learn a separate safety policy that excludes those unsafe behaviors. In addition, AdvEx-RL ensures safety in a task-agnostic manner by acting as a safety firewall and therefore can be integrated with any RL task policy. We demonstrate the robustness of AdvEx-RL via comprehensive experiments in standard constrained Markov decision processes (CMDP) environments under 2 white-box action space perturbations as well as with changes in environment dynamics against 7 baselines. Consistently, AdvEx-RL outperforms the baselines by achieving an average safety performance of over 75% in the continuous action space with 10 times more variations in the testing environment dynamics. By using a standalone safety policy independent of conflicting objectives, AdvEx-RL also paves the way for interpretable safety behavior analysis as we show in our user study.
{"title":"Adversarial Behavior Exclusion for Safe Reinforcement Learning","authors":"Md Asifur Rahman, Tongtong Liu, Sarra M. Alqahtani","doi":"10.24963/ijcai.2023/54","DOIUrl":"https://doi.org/10.24963/ijcai.2023/54","url":null,"abstract":"Learning by exploration makes reinforcement learning (RL) potentially attractive for many real-world applications. However, this learning process makes RL inherently too vulnerable to be used in real-world applications where safety is of utmost importance. Most prior studies consider exploration at odds with safety and thereby restrict it using either joint optimization of task and safety or imposing constraints for safe exploration. This paper migrates from the current convention to using exploration as a key to safety by learning safety as a robust behavior that completely excludes any behavioral pattern responsible for safety violations. Adversarial Behavior Exclusion for Safe RL (AdvEx-RL) learns a behavioral representation of the agent's safety violations by approximating an optimal adversary utilizing exploration and later uses this representation to learn a separate safety policy that excludes those unsafe behaviors. In addition, AdvEx-RL ensures safety in a task-agnostic manner by acting as a safety firewall and therefore can be integrated with any RL task policy. We demonstrate the robustness of AdvEx-RL via comprehensive experiments in standard constrained Markov decision processes (CMDP) environments under 2 white-box action space perturbations as well as with changes in environment dynamics against 7 baselines. Consistently, AdvEx-RL outperforms the baselines by achieving an average safety performance of over 75% in the continuous action space with 10 times more variations in the testing environment dynamics. By using a standalone safety policy independent of conflicting objectives, AdvEx-RL also paves the way for interpretable safety behavior analysis as we show in our user study.","PeriodicalId":394530,"journal":{"name":"International Joint Conference on Artificial Intelligence","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122176768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：