A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
The paper discusses the shift from traditional storage systems to in situ AI that provides multi-level abstractions for accessing information content from raw bits to learned functions capturing distributions.
Unknown
ONELIFE learns symbolic world models from a single unguided exploration episode using programmatic representations and stochastic abstractions.
Tom Dietterich
Introduces the MAXQ decomposition for hierarchical reinforcement learning, enabling faster convergence via state abstractions and recursively optimal policies.