The Essence and Main Differences of Consumer Societies from Credit Consumer Cooperatives in the Light of Attracting Citizens' Funds

The article is devoted to the comparative analysis of the essence of consumer and credit cooperatives in the context of attracting citizens' funds, the transformation of their economic processes and functions in the genesis of microeconomic development. The research is based on the analysis of historical documents and Russian publications, as well as on statistical conclusions of economic data. The aim of the study was to study the evolution of consumer societies and credit cooperatives as instruments for attracting household finances on the example of Russian and foreign companies since the middle of the XIX century. Semantic definitions of the categories consumer society and consumer credit cooperative, tasks and historical stages of the development of the studied communication tools in the field of attracting the means of the population are determined. The author's experience of comparative characteristics of the analyzed economic entities is proposed, reflecting the risks, advantages and disadvantages of the studied communication objects. The functions of the Bank of Russia as the main regulator of consumer credit cooperatives are disclosed. The final results of the study substantiate the importance of financial literacy and present an algorithm that allows the population to distinguish the legal activities of consumer credit cooperatives from fraudsters.

Generating individual intrinsic reward for cooperative multiagent reinforcement learning

Multiagent reinforcement learning holds considerable promise to deal with cooperative multiagent tasks. Unfortunately, the only global reward shared by all agents in the cooperative tasks may lead to the lazy agent problem. To cope with such a problem, we propose a generating individual intrinsic reward algorithm, which introduces an intrinsic reward encoder to generate an individual intrinsic reward for each agent and utilizes the hypernetworks as the decoder to help to estimate the individual action values of the decomposition methods based on the generated individual intrinsic reward. Experimental results in the StarCraft II micromanagement benchmark prove that the proposed algorithm can increase learning efficiency and improve policy performance.

MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks

Value function decomposition (VFD) methods under the popular paradigm of centralized training and decentralized execution (CTDE) have promoted multi-agent reinforcement learning progress. However, existing VFD methods proceed from a group's value function decomposition to only solve cooperative tasks. With the individual value function decomposition, we propose MFVFD, a novel multi-agent Q-learning approach for solving cooperative and non-cooperative tasks based on mean-field theory. Our analysis on the Hawk-Dove and Nonmonotonic Cooperation matrix games evaluate MFVFD's convergent solution. Empirical studies on the challenging mixed cooperative-competitive tasks where hundreds of agents coexist demonstrate that MFVFD significantly outperforms existing baselines.

Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

This paper investigates the model-based methods in multi-agent reinforcement learning (MARL). We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound. To reduce the upper bound with the intention of low sample complexity during the whole learning process, we propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy Optimization (AORPO). In AORPO, each agent builds its multi-agent environment model, consisting of a dynamics model and multiple opponent models, and trains its policy with the adaptive opponent-wise rollout. We further prove the theoretic convergence of AORPO under reasonable assumptions. Empirical experiments on competitive and cooperative tasks demonstrate that AORPO can achieve improved sample efficiency with comparable asymptotic performance over the compared MARL methods.

A Real Application of an Autonomous Industrial Mobile Manipulator within Industrial Context

In modern industry there are still a large number of low added-value processes that can be automated or semi-automated with safe cooperation between robot and human operators. The European SHERLOCK project aims to integrate an autonomous industrial mobile manipulator (AIMM) to perform cooperative tasks between a robot and a human. To be able to do this, AIMMs need to have a variety of advanced cognitive skills like autonomous navigation, smart perception and task management. In this paper, we report the project’s tackle in a paradigmatic industrial application combining accurate autonomous navigation with deep learning-based 3D perception for pose estimation to locate and manipulate different industrial objects in an unstructured environment. The proposed method presents a combination of different technologies fused in an AIMM that achieve the proposed objective with a success rate of 83.33% in tests carried out in a real environment.