Výsledky vyhledávání - "Pina, Rafael"

Report

Fully Independent Communication in Multi-Agent Reinforcement Learning

Autor: Pina, Rafael, De Silva, Varuna, Artaud, Corentin, Liu, Xiaolan

Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. Several recent works have focused specifically on the study of communication approaches in MARL. While multiple communication method

Externí odkaz: http://arxiv.org/abs/2401.15059

Zobrazit plný text záznamu

Report

Staged Reinforcement Learning for Complex Tasks through Decomposed Environments

Autor: Pina, Rafael, Artaud, Corentin, Liu, Xiaolan, De Silva, Varuna

Reinforcement Learning (RL) is an area of growing interest in the field of artificial intelligence due to its many notable applications in diverse fields. Particularly within the context of intelligent vehicle control, RL has made impressive progress

Externí odkaz: http://arxiv.org/abs/2311.02746

Zobrazit plný text záznamu

Report

Learning Independently from Causality in Multi-Agent Environments

Autor: Pina, Rafael, De Silva, Varuna, Artaud, Corentin

Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in MARL that

Externí odkaz: http://arxiv.org/abs/2311.02741

Zobrazit plný text záznamu

Report

Discovering Causality for Efficient Cooperation in Multi-Agent Environments

Autor: Pina, Rafael, De Silva, Varuna, Artaud, Corentin

In cooperative Multi-Agent Reinforcement Learning (MARL) agents are required to learn behaviours as a team to achieve a common goal. However, while learning a task, some agents may end up learning sub-optimal policies, not contributing to the objecti

Externí odkaz: http://arxiv.org/abs/2306.11846

Zobrazit plný text záznamu

Report

Embedding Contextual Information through Reward Shaping in Multi-Agent Learning: A Case Study from Google Football

Autor: Gu, Chaoyi, De Silva, Varuna, Artaud, Corentin, Pina, Rafael

Publikováno v: 2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS), Guayaquil, Ecuador, 2023, pp. 1-8

Artificial Intelligence has been used to help human complete difficult tasks in complicated environments by providing optimized strategies for decision-making or replacing the manual labour. In environments including multiple agents, such as football

Externí odkaz: http://arxiv.org/abs/2303.15471

Zobrazit plný text záznamu

Report

Causality Detection for Efficient Multi-Agent Reinforcement Learning

Autor: Pina, Rafael, De Silva, Varuna, Artaud, Corentin

When learning a task as a team, some agents in Multi-Agent Reinforcement Learning (MARL) may fail to understand their true impact in the performance of the team. Such agents end up learning sub-optimal policies, demonstrating undesired lazy behaviour

Externí odkaz: http://arxiv.org/abs/2303.14227

Zobrazit plný text záznamu

Report

Residual Q-Networks for Value Function Factorizing in Multi-Agent Reinforcement Learning

Autor: Pina, Rafael, De Silva, Varuna, Hook, Joosep, Kondoz, Ahmet

Multi-Agent Reinforcement Learning (MARL) is useful in many problems that require the cooperation and coordination of multiple agents. Learning optimal policies using reinforcement learning in a multi-agent setting can be very difficult as the number

Externí odkaz: http://arxiv.org/abs/2205.15245

Zobrazit plný text záznamu