RL on Graphs 🚶
Learning to Walk with Dual Agents for Knowledge Graph Reasoning (AAAI'22)
Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout
High throughput synchronous and asynchronous reinforcement learning
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".
Must-read papers on knowledge graph reasoning
Code and models for the paper Path Reasoning over Knowledge Graph: A Multi-Agent and Reinforcement Learning Based Method
Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
This collection of papers can be used to summarize research about graph reinforcement learning for the convenience of researchers.
Reinforcement Knowledge Graph Reasoning for Explainable Recommendation