AquaAqua's repositories
manager-worker-mtsptwr
Official implementation of paper "Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning"
RLGNN-JSSP
A reimplementation of paper "Learning to schedule job-shop problems: representation and policy learning using graph neural network and reinforcement learning"
ScheduleNet
A reimplement of paper "ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning "
DAGNN
A graph neural network tailored to directed acyclic graphs that outperforms conventional GNNs by leveraging the partial order as strong inductive bias besides other suitable architectural features.
DPRM
Our paper "Aligning Crowd Feedback via Distributional Preference Reward modelling"
grok-1
Grok open release