Zobrazeno 1 - 10
of 1 418
pro vyhledávání: '"Nowé A"'
With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes a concern. Programmatic Reinforcement Learning (PRL) is able to to cr
Externí odkaz:
http://arxiv.org/abs/2410.21940
Publikováno v:
Reinforcement Learning Journal, vol. 1, no. 1, 2024, pp. TBD
In key real-world problems, full state information is sometimes available but only at a high cost, like activating precise yet energy-intensive sensors or consulting humans, thereby compelling the agent to operate under partial observability. For thi
Externí odkaz:
http://arxiv.org/abs/2407.18812
Autor:
Felten, Florian, Ucak, Umut, Azmani, Hicham, Peng, Gao, Röpke, Willem, Baier, Hendrik, Mannion, Patrick, Roijers, Diederik M., Terry, Jordan K., Talbi, El-Ghazali, Danoy, Grégoire, Nowé, Ann, Rădulescu, Roxana
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers
Externí odkaz:
http://arxiv.org/abs/2407.16312
We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific seq
Externí odkaz:
http://arxiv.org/abs/2404.03596
Individual and social biases undermine the effectiveness of human advisers by inducing judgment errors which can disadvantage protected groups. In this paper, we study the influence these biases can have in the pervasive problem of fake news by evalu
Externí odkaz:
http://arxiv.org/abs/2403.08829
Autor:
Delgrange, Florent, Avni, Guy, Lukina, Anna, Schilling, Christian, Nowé, Ann, Pérez, Guillermo A.
We propose a novel approach to the problem of controller design for environments modeled as Markov decision processes (MDPs). Specifically, we consider a hierarchical MDP a graph with each vertex populated by an MDP called a "room". We first apply de
Externí odkaz:
http://arxiv.org/abs/2402.13785
Autor:
Röpke, Willem, Reymond, Mathieu, Mannion, Patrick, Roijers, Diederik M., Nowé, Ann, Rădulescu, Roxana
A significant challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies that attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), a principled algorithm t
Externí odkaz:
http://arxiv.org/abs/2402.07182
Communication plays a vital role in multi-agent systems, fostering collaboration and coordination. However, in real-world scenarios where communication is bandwidth-limited, existing multi-agent reinforcement learning (MARL) algorithms often provide
Externí odkaz:
http://arxiv.org/abs/2306.10134
Autor:
Röpke, Willem, Hayes, Conor F., Mannion, Patrick, Howley, Enda, Nowé, Ann, Roijers, Diederik M.
For effective decision support in scenarios with conflicting objectives, sets of potentially optimal solutions can be presented to the decision maker. We explore both what policies these sets should contain and how such sets can be computed efficient
Externí odkaz:
http://arxiv.org/abs/2305.05560
Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work we model such changes in d
Externí odkaz:
http://arxiv.org/abs/2305.01063