Skip to main content

Directed Evolution with Transformer

Project description

Transformer RL Directed Evolution (wip)

Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster

Citations

@article{Song2023ReinforcementLE,
    title   = {Reinforcement Learning-assisted Evolutionary Algorithm: A Survey and Research Opportunities},
    author  = {Yanjie Song and Yutong Wu and Yangyang Guo and Ran Yan and Ponnuthurai Nagaratnam and Suganthan and Yue Zhang and Witold Pedrycz and Ying Wu Chen and Swagatam Das and R. Mallipeddi and Solomon Ajani},
    journal = {Swarm Evol. Comput.},
    year   = {2023},
    volume = {86},
    pages  = {101517},
    url    = {https://api.semanticscholar.org/CorpusID:261214753}
}
@inproceedings{mysore2022multicritic,
    title   = {Multi-Critic Actor Learning: Teaching {RL} Policies to Act with Style},
    author  = {Siddharth Mysore and George Cheng and Yunqi Zhao and Kate Saenko and Meng Wu},
    booktitle = {International Conference on Learning Representations},
    year    = {2022},
    url     = {https://openreview.net/forum?id=rJvY_5OzoI}
}
@article{ShemTov2024DeepNC,
    title  = {Deep Neural Crossover: A Multi-Parent Operator That Leverages Gene Correlations},
    author = {Eliad Shem-Tov and Achiya Elyasaf},
    journal = {Proceedings of the Genetic and Evolutionary Computation Conference},
    year   = {2024},
    url    = {https://api.semanticscholar.org/CorpusID:268512900}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

transformer_directed_evolution-0.0.3.tar.gz (8.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file transformer_directed_evolution-0.0.3.tar.gz.

File metadata

File hashes

Hashes for transformer_directed_evolution-0.0.3.tar.gz
Algorithm Hash digest
SHA256 b632302394844911cf07d3020f3971491d86a6210aab130dd263bf36885cf3a8
MD5 d030afea79e82aca300bada4b8d7616c
BLAKE2b-256 38d6887a990bcd9ba2eb8abdb756380d562e6fd4b2ea14f49dfe9edab2153ef6

See more details on using hashes here.

File details

Details for the file transformer_directed_evolution-0.0.3-py3-none-any.whl.

File metadata

File hashes

Hashes for transformer_directed_evolution-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 627311843a458d2d55dd9ebf1197310582b111232ff4403986f7f77905e60a34
MD5 413ced51d8245dd84a0fa826f79a6ab9
BLAKE2b-256 4b02bf04e3d1336edd174cdb5995fd3ec9728c3fb20d6cbf5707ce5c0904e956

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page