In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of NetHack by interacting with the NetHack Learning Environment (NLE), a scalable, procedurally generated, and challenging Gym environment for reinforcement learning (RL). The challenge showcased communitydriven progress in AI with many diverse approaches significantly beating the previously best results on NetHack. Furthermore, it served as a direct comparison between neural (e.g., deep RL) and symbolic AI, as well as hybrid systems, demonstrating that on NetHack symbolic bots currently outperform deep RL by a large margin. Lastly, no agent got close to winning the game, illustrating NetHack's suitability as a long-term benchmark for AI research.
Many tasks in graph machine learning, such as link prediction and node classification, are typically solved using representation learning. Each node or edge in the network is encoded via an embedding. Though there exists a lot of network embeddings for static graphs, the task becomes much more complicated when the dynamic (i.e., temporal) network is analyzed. In this paper, we propose a novel approach for dynamic network representation learning based on Temporal Graph Network by using a highly custom message generating function by extracting Causal Anonymous Walks. We provide a benchmark pipeline for the evaluation of temporal network embeddings. This work provides the first comprehensive comparison framework for temporal network representation learning for graph machine learning problems involving node classification and link prediction in every available setting. The proposed model outperforms state-of-the-art baseline models. The work also justifies their difference based on evaluation in various transductive/inductive edge/node classification tasks. In addition, we show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks, involving credit scoring based on transaction data.
In this paper we present a novel approach to credit scoring of retail customers in the banking industry based on deep learning methods. We used RNNs on fine grained transnational data to compute credit scores for the loan applicants. We demonstrate that our approach significantly outperforms the baselines based on the customer data of a large European bank. We also conducted a pilot study on loan applicants of the bank, and the study produced significant financial gains for the organization. In addition, our method has several other advantages described in the paper that are very significant for the bank.
Based on the analysis of users dialogues and chatbots presented on the websites of German commercial firms, the article describes the linguistic and pragmatic features of human interaction with «virtual assistants», specifies the characteristics of chatbots and the texts generated by them, characteristics that make interactions anthropomorphic, and the parameters are also determined that indicate the artificiality of the communication between the client and the chatbot. The interaction of the user and the program created on the basis of artificial intelligence is carried out using the language of «daily people communication», therefore, this communicative interaction is considered in the article as a separate discursive practice with its own characteristics. The article notes that so far, when studying the interaction of customers and chatbots, the main focus has been on technical, economic and social aspects, but not linguistic ones. The empirical study of user dialogues with «virtual assistants» presented in the work contains conclusions that are of interest for formulating recommendations to clients who turn to communication services in order to obtain information about any product or service, as well as to representatives of Internet commerce and IT developers, who are developing concepts for using chatbots in sales.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.