Interesting Engineering

New safety-critical cockpit automation engine unveiled to minimize flight plan data errors

The technology introduces a traceable, multi-model system designed to support pilots and flight operators using established ...
IEEE

Sample Efficient Deep Reinforcement Learning With Online State Abstraction and Causal Transformer Model Prediction

Abstract: Deep reinforcement learning (RL) typically requires a tremendous number of training samples, which are not practical in many applications. State abstraction and world models are two ...
IEEE

Sample Trajectory Selection Method Based on Large Language Model in Reinforcement Learning

Abstract: This paper introduces a method for trajectory selection using large-scale pre-trained language models, aiming to improve sample and training efficiency in reinforcement learning. By using a ...