Zobrazeno 1 - 10
of 425
pro vyhledávání: '"Montana Giovanni"'
Traditional offline reinforcement learning methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of distributional shift but res
Externí odkaz:
http://arxiv.org/abs/2405.14374
Autor:
Ireland, David, Montana, Giovanni
Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent reinforcem
Externí odkaz:
http://arxiv.org/abs/2401.08850
Publikováno v:
Transactions on Machine Learning Research (05/2024)
Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face constrain
Externí odkaz:
http://arxiv.org/abs/2310.20025
The graph colouring problem consists of assigning labels, or colours, to the vertices of a graph such that no two adjacent vertices share the same colour. In this work we investigate whether deep reinforcement learning can be used to discover a compe
Externí odkaz:
http://arxiv.org/abs/2304.04051
Autor:
Beeson, Alex, Montana, Giovanni
Offline reinforcement learning agents seek optimal policies from fixed data sets. With environmental interaction prohibited, agents face significant challenges in preventing errors in value estimates from compounding and subsequently causing the lear
Externí odkaz:
http://arxiv.org/abs/2303.14716
Publikováno v:
Machine Learning (ECML-PKDD 2023 Journal Track)
Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets. This is a particularly difficult setup, especially when learning to achieve multiple different goals or outcomes under a given scenario with o
Externí odkaz:
http://arxiv.org/abs/2303.09367
Autor:
Hepburn, Charles A., Montana, Giovanni
Behavioural cloning (BC) is a commonly used imitation learning method to infer a sequential decision-making policy from expert demonstrations. However, when the quality of the data is not optimal, the resulting behavioural policy also performs sub-op
Externí odkaz:
http://arxiv.org/abs/2212.04280
Autor:
Beeson, Alex, Montana, Giovanni
The ability to discover optimal behaviour from fixed data sets has the potential to transfer the successes of reinforcement learning (RL) to domains where data collection is acutely problematic. In this offline setting, a key challenge is overcoming
Externí odkaz:
http://arxiv.org/abs/2211.11802
Autor:
Hepburn, Charles A., Montana, Giovanni
In many real-world applications, collecting large and high-quality datasets may be too costly or impractical. Offline reinforcement learning (RL) aims to infer an optimal decision-making policy from a fixed set of data. Getting the most information f
Externí odkaz:
http://arxiv.org/abs/2211.11603
Autor:
MacPherson, Matthew, Muthuswamy, Keerthini, Amlani, Ashik, Hutchinson, Charles, Goh, Vicky, Montana, Giovanni
Understanding the internal physiological changes accompanying the aging process is an important aspect of medical image interpretation, with the expected changes acting as a baseline when reporting abnormal findings. Deep learning has recently been d
Externí odkaz:
http://arxiv.org/abs/2207.01302