AlphaUncommon
salesforce/MultiHopKG
Multi-hop knowledge graph reasoning learned via policy gradient with reward shaping and action dropout
Archived: this repository is read-only
- Owner
- salesforce (organization)
- Stars
- Stars: 316
- Forks
- Forks: 78
- Language
- Jupyter Notebook
- License
- BSD-3-Clause
- Created
- 2018
- Topics
- policy-gradientreinforcement-learningreward-shapingaction-dropoutpytorchknowledge-graphmulti-hop-reasoning
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by salesforce
All 97 repos by salesforce- salesforce/LAVISStars: 11,257Jupyter NotebookStable
- salesforce/BLIPStars: 5,703Jupyter NotebookStable
- salesforce/CodeGenStars: 5,183PythonStable
- salesforce/MerlionStars: 4,488PythonRC
- salesforce/akitaStars: 3,662TypeScriptRC
- salesforce/ja3Stars: 3,097PythonRC
Nearby in Jupyter Notebook
All Jupyter Notebook repos- AnswerDotAI/claudetteStars: 316Jupyter NotebookAlpha
- nebius/token-factory-cookbookStars: 316Jupyter NotebookAlpha
- zorost/AI-Engineering-LabStars: 316Jupyter NotebookAlpha
- demidovakatya/mashinnoye-obucheniyeStars: 316Jupyter NotebookAlpha
- thuijskens/bayesian-optimizationStars: 316Jupyter NotebookAlpha
- noahgift/functional_intro_to_pythonStars: 316Jupyter NotebookAlpha