Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Entropy-Based Characterisation of the Polarised Regime in Latent Variable Models
Peter Clapham, Lisa Bonheme, Marek Grzes
Variational Autoencoders (VAEs) often exhibit a polarised regime in which latent variables separate into active, passive, and mixed subsets. Existing criteria for identifying activ…
cs.LG2024
Structure learning with Temporal Gaussian Mixture for model-based Reinforcement Learning
Théophile Champion, Marek GrzeÅ, Howard Bowman
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 subs…