Computer ScienceICLR 2024
Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
C. Gumbsch, N. Sajid, et al.
THICK (Temporal Hierarchies from Invariant Context Kernels) learns hierarchical world models with discrete latent dynamics: a low level that sparsely updates invariant contexts and a high level that predicts context changes, producing interpretable temporal abstractions and improved model-based RL and planning. Research conducted by Christian Gumbsch, Noor Sajid, Georg Martius, and Martin V. Butz.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Computer Science
Simplifying Latent Dynamics with Softly State-Invariant World Models
T. Saanum, P. Dayan, et al.
Computer Science
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
N. Dainese, M. Alakuijala, et al.
Education
Math items about real-world content lower test-scores of students from families with low socioeconomic status
M. Muskens, W. E. Frankenhuis, et al.
Medicine and Health
Comparison of NLP machine learning models with human physicians for ASA Physical Status classification
S. B. Yoon, J. Lee, et al.
