New model frames human reinforcement learning in the context of memory and habits

Humans and most other animals are known to be strongly driven by expected rewards or adverse consequences. The process of ...
IEEE

The Parallel Chaotification Map and Its Application

Abstract: A universal modular plus parallel (MPP) method is proposed to construct enhanced chaotic maps, including one-dimensional MPP chaotic map (1D-MPPCM) and high-dimensional MPPCM (HD-MPPCM). It ...
GitHub

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.
IEEE

A Novel Single-Driver Series-Parallel IGBTs Solid State Circuit Breaker Component

Abstract: Solid-state dc circuit breaker (SSCB) has become a key component for fast fault isolation in high-voltage dc systems. However, their effectiveness often relies on complex series and parallel ...