A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Curious Meta-Controller alternates between model-based and model-free control to improve sample efficiency.
This paper improves robot grasping by integrating meta-control and latent-space imagination.
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that…
RG-TTA adapts neural forecasters to streaming time series shifts by modulating adaptation intensity.
Enhances exploration in hierarchical networks using mutual information.
A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual interaction environment that allows many types of tasks to be unified in a single…
CNAS optimizes neural architectures for class-incremental learning.
GeNAS uses genetic algorithms to automatically assess human sperm morphology.