Zobrazeno 1 - 10
of 1 029
pro vyhledávání: '"Prorok, P."'
Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic exploration emerg
Externí odkaz:
http://arxiv.org/abs/2410.04988
Autor:
Mokhtarian, Armin, Xu, Jianye, Scheffe, Patrick, Kloock, Maximilian, Schäfer, Simon, Bang, Heeseung, Le, Viet-Anh, Ulhas, Sangeet, Betz, Johannes, Wilson, Sean, Berman, Spring, Paull, Liam, Prorok, Amanda, Alrifaee, Bassam
Connected and automated vehicles and robot swarms hold transformative potential for enhancing safety, efficiency, and sustainability in the transportation and manufacturing sectors. Extensive testing and validation of these technologies is crucial fo
Externí odkaz:
http://arxiv.org/abs/2408.14199
We present a method for developing navigation policies for multi-robot teams that interpret and follow natural language instructions. We condition these policies on embeddings from pretrained Large Language Models (LLMs), and train them via offline r
Externí odkaz:
http://arxiv.org/abs/2407.20164
Autor:
Toledo, Edan, Prorok, Amanda
Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer, an extension of the Dreamer
Externí odkaz:
http://arxiv.org/abs/2406.13600
The study of behavioral diversity in Multi-Agent Reinforcement Learning (MARL) is a nascent yet promising field. In this context, the present work deals with the question of how to control the diversity of a multi-agent system. With no existing appro
Externí odkaz:
http://arxiv.org/abs/2405.15054
Compact robotic platforms with powerful compute and actuation capabilities are key enablers for practical, real-world deployments of multi-agent research. This article introduces a tightly integrated hardware, control, and simulation software stack o
Externí odkaz:
http://arxiv.org/abs/2405.02198
Autonomous robot operation in unstructured environments is often underpinned by spatial understanding through vision. Systems composed of multiple concurrently operating robots additionally require access to frequent, accurate and reliable pose estim
Externí odkaz:
http://arxiv.org/abs/2405.01107
The $3$-colourability problem is a well-known NP-complete problem and it remains NP-complete for $bull$-free graphs, where $bull$ is the graph consisting of $K_3$ with two pendant edges attached to two of its vertices. In this paper we study $3$-colo
Externí odkaz:
http://arxiv.org/abs/2404.12515
This work views the multi-agent system and its surrounding environment as a co-evolving system, where the behavior of one affects the other. The goal is to take both agent actions and environment configurations as decision variables, and optimize the
Externí odkaz:
http://arxiv.org/abs/2403.14583
Existing communication methods for multi-agent reinforcement learning (MARL) in cooperative multi-robot problems are almost exclusively task-specific, training new communication strategies for each unique task. We address this inefficiency by introdu
Externí odkaz:
http://arxiv.org/abs/2403.06750