Evolution Guided Generative Flow Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918057205563392 |
|---|---|
| author | Ikram, Zarif Pan, Ling Liu, Dianbo |
| author_facet | Ikram, Zarif Pan, Ling Liu, Dianbo |
| contents | Generative Flow Networks (GFlowNets) are a family of probabilistic generative models that learn to sample compositional objects proportional to their rewards. One big challenge of GFlowNets is training them effectively when dealing with long time horizons and sparse rewards. To address this, we propose Evolution guided generative flow networks (EGFN), a simple but powerful augmentation to the GFlowNets training using Evolutionary algorithms (EA). Our method can work on top of any GFlowNets training objective, by training a set of agent parameters using EA, storing the resulting trajectories in the prioritized replay buffer, and training the GFlowNets agent using the stored trajectories. We present a thorough investigation over a wide range of toy and real-world benchmark tasks showing the effectiveness of our method in handling long trajectories and sparse rewards. We release the code at http://github.com/zarifikram/egfn. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02186 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evolution Guided Generative Flow Networks Ikram, Zarif Pan, Ling Liu, Dianbo Machine Learning Artificial Intelligence Generative Flow Networks (GFlowNets) are a family of probabilistic generative models that learn to sample compositional objects proportional to their rewards. One big challenge of GFlowNets is training them effectively when dealing with long time horizons and sparse rewards. To address this, we propose Evolution guided generative flow networks (EGFN), a simple but powerful augmentation to the GFlowNets training using Evolutionary algorithms (EA). Our method can work on top of any GFlowNets training objective, by training a set of agent parameters using EA, storing the resulting trajectories in the prioritized replay buffer, and training the GFlowNets agent using the stored trajectories. We present a thorough investigation over a wide range of toy and real-world benchmark tasks showing the effectiveness of our method in handling long trajectories and sparse rewards. We release the code at http://github.com/zarifikram/egfn. |
| title | Evolution Guided Generative Flow Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.02186 |