Zobrazeno 1 - 10
of 89
pro vyhledávání: '"Grześ, Marek"'
Model-based reinforcement learning refers to a set of approaches capable of sample-efficient decision making, which create an explicit model of the environment. This model can subsequently be used for learning optimal policies. In this paper, we prop
Externí odkaz:
http://arxiv.org/abs/2411.11511
Autor:
Grzes, Marek
This thesis presents novel work on how to improve exploration in reinforcement learning using domain knowledge and knowledge-based approaches to reinforcement learning. It also identifies novel relationships between the algorithms' and domains' param
Externí odkaz:
http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.520040
Active inference is a leading theory of perception, learning and decision making, which can be applied to neuroscience, robotics, psychology, and machine learning. Active inference is based on the expected free energy, which is mostly justified by th
Externí odkaz:
http://arxiv.org/abs/2402.14460
This study examines the ability of GPT-3.5, GPT-3.5-turbo (ChatGPT) and GPT-4 models to generate poems in the style of specific authors using zero-shot and many-shot prompts (which use the maximum context length of 8192 tokens). We assess the perform
Externí odkaz:
http://arxiv.org/abs/2305.11064
Autor:
Bonheme, Lisa, Grzes, Marek
Variational autoencoders (VAEs) are used for transfer learning across various research domains such as music generation or medical image analysis. However, there is no principled way to assess before transfer which components to retrain or whether tr
Externí odkaz:
http://arxiv.org/abs/2304.10767
Active inference is a theory of perception, learning and decision making, which can be applied to neuroscience, robotics, and machine learning. Recently, reasearch has been taking place to scale up this framework using Monte-Carlo tree search and dee
Externí odkaz:
http://arxiv.org/abs/2303.01618
This paper presents the Crowd Score, a novel method to assess the funniness of jokes using large language models (LLMs) as AI judges. Our method relies on inducing different personalities into the LLM and aggregating the votes of the AI judges into a
Externí odkaz:
http://arxiv.org/abs/2212.11214
Autor:
Bonheme, Lisa, Grzes, Marek
When training a variational autoencoder (VAE) on a given dataset, determining the optimal number of latent variables is mostly done by grid search: a costly process in terms of computational time and carbon footprint. In this paper, we explore the in
Externí odkaz:
http://arxiv.org/abs/2209.12806
Active inference is a state-of-the-art framework for modelling the brain that explains a wide range of mechanisms such as habit formation, dopaminergic discharge and curiosity. Recently, two versions of branching time active inference (BTAI) based on
Externí odkaz:
http://arxiv.org/abs/2206.12503
Autor:
Bonheme, Lisa, Grzes, Marek
The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications. However, their behaviour is not yet fully understood. For example, the questions of when they can provide disentang
Externí odkaz:
http://arxiv.org/abs/2205.08399