Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Papoudakis, Georgios"'
Autor:
Christianos, Filippos, Papoudakis, Georgios, Coste, Thomas, Hao, Jianye, Wang, Jun, Shao, Kun
This paper introduces a novel mobile phone control architecture, termed ``app agents", for efficient interactions and controls across various Android apps. The proposed Lightweight Multi-modal App Control (LiMAC) takes as input a textual goal and a s
Externí odkaz:
http://arxiv.org/abs/2410.17883
Autor:
Christianos, Filippos, Papoudakis, Georgios, Zimmer, Matthieu, Coste, Thomas, Wu, Zhihao, Chen, Jingxuan, Khandelwal, Khyati, Doran, James, Feng, Xidong, Liu, Jiacheng, Xiong, Zheng, Luo, Yicheng, Hao, Jianye, Shao, Kun, Bou-Ammar, Haitham, Wang, Jun
A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of generali
Externí odkaz:
http://arxiv.org/abs/2312.14878
Autor:
Krnjaic, Aleksandar, Steleac, Raul D., Thomas, Jonathan D., Papoudakis, Georgios, Schäfer, Lukas, To, Andrew Wing Keung, Lao, Kuan-Ho, Cubuktepe, Murat, Haley, Matthew, Börsting, Peter, Albrecht, Stefano V.
We consider a warehouse in which dozens of mobile robots and human pickers work together to collect and deliver items within the warehouse. The fundamental problem we tackle, called the order-picking problem, is how these worker agents must coordinat
Externí odkaz:
http://arxiv.org/abs/2212.11498
This work focuses on equilibrium selection in no-conflict multi-agent games, where we specifically study the problem of selecting a Pareto-optimal Nash equilibrium among several existing equilibria. It has been shown that many state-of-the-art multi-
Externí odkaz:
http://arxiv.org/abs/2209.14344
Autor:
Ahmed, Ibrahim H., Brewitt, Cillian, Carlucho, Ignacio, Christianos, Filippos, Dunion, Mhairi, Fosong, Elliot, Garcin, Samuel, Guo, Shangmin, Gyevnar, Balint, McInroe, Trevor, Papoudakis, Georgios, Rahman, Arrasy, Schäfer, Lukas, Tamborski, Massimiliano, Vecchio, Giuseppe, Wang, Cheng, Albrecht, Stefano V.
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel ma
Externí odkaz:
http://arxiv.org/abs/2208.01769
Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable parameters, short
Externí odkaz:
http://arxiv.org/abs/2102.07475
Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled ag
Externí odkaz:
http://arxiv.org/abs/2006.09447
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three different cla
Externí odkaz:
http://arxiv.org/abs/2006.07869
Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact with the
Externí odkaz:
http://arxiv.org/abs/2001.10829
Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains. A particular approach which has received increasing attention is multi-agent reinforcement learni
Externí odkaz:
http://arxiv.org/abs/1906.04737