Transformer Metacontroller

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for lucidrains from gravatar.com lucidrains

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: MIT License (MIT License)
  • Author: Phil Wang
  • Tags artificial intelligence , deep learning , hierarchical reinforcement learning , latent steering
  • Requires: Python >=3.9
  • Provides-Extra: examples , test
Classifiers
Report project as malware

Project description

metacontroller (wip)

Implementation of the MetaController proposed in Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Install

$ pip install metacontroller-pytorch

Appreciation

  • Pranoy for submitting a pull request for fixing the previous latent action not being included in the inputs to the switching unit

  • Diego Calanzone for proposing testing on BabyAI gridworld task, and submitting the pull request for behavior cloning and discovery phase training for it!

Citations

@misc{kobayashi2025emergenttemporalabstractionsautoregressive,
    title   = {Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning}, 
    author  = {Seijin Kobayashi and Yanick Schimpf and Maximilian Schlegel and Angelika Steger and Maciej Wolczyk and Johannes von Oswald and Nino Scherrer and Kaitlin Maile and Guillaume Lajoie and Blake A. Richards and Rif A. Saurous and James Manyika and Blaise Agüera y Arcas and Alexander Meulemans and João Sacramento},
    year    = {2025},
    eprint  = {2512.20605},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url     = {https://arxiv.org/abs/2512.20605}, 
}

@article{Wagenmaker2025SteeringYD,
    title   = {Steering Your Diffusion Policy with Latent Space Reinforcement Learning},
    author  = {Andrew Wagenmaker and Mitsuhiko Nakamoto and Yunchu Zhang and Seohong Park and Waleed Yagoub and Anusha Nagabandi and Abhishek Gupta and Sergey Levine},
    journal = {ArXiv},
    year    = {2025},
    volume  = {abs/2506.15799},
    url     = {https://api.semanticscholar.org/CorpusID:279464702}
}

@misc{hwang2025dynamicchunkingendtoendhierarchical,
    title   = {Dynamic Chunking for End-to-End Hierarchical Sequence Modeling},
    author  = {Sukjun Hwang and Brandon Wang and Albert Gu},
    year    = {2025},
    eprint  = {2507.07955},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url     = {https://arxiv.org/abs/2507.07955},
}

@misc{fleuret2025freetransformer,
    title     = {The Free Transformer}, 
    author    = {François Fleuret},
    year      = {2025},
    eprint    = {2510.17558},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url       = {https://arxiv.org/abs/2510.17558}, 
}

Life can only be understood backwards; but it must be lived forwards - Søren Kierkegaard

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for lucidrains from gravatar.com lucidrains

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: MIT License (MIT License)
  • Author: Phil Wang
  • Tags artificial intelligence , deep learning , hierarchical reinforcement learning , latent steering
  • Requires: Python >=3.9
  • Provides-Extra: examples , test
Classifiers

Release history Release notifications | RSS feed

0.2.49

0.2.48

0.2.46

0.2.45

0.2.44

0.2.43

0.2.42

0.2.41

0.2.40

0.2.39

0.2.38

0.2.37

0.2.36

0.2.35

0.2.34

0.2.33

0.2.32

0.2.31

0.2.30

0.2.29

0.2.28

0.2.27

0.2.26

0.2.25

0.2.24

0.2.23

0.2.22

0.2.21

0.2.20

0.2.19

0.2.18

0.2.17

0.2.16

0.2.15

0.2.14

0.2.12

0.2.10

0.2.5

0.2.4

0.2.3

0.2.2

0.2.1

0.2.0

0.1.30

0.1.28

0.1.27

0.1.26

0.1.25

0.1.24

0.1.23

0.1.22

0.1.21

0.1.20

0.1.19

0.1.18

0.1.17

0.1.16

0.1.15

0.1.14

0.1.12

0.1.11

0.1.10

0.1.9

0.1.8

0.1.7

0.1.6

0.1.5

0.1.4

0.1.2

0.1.0

0.0.70

0.0.69

0.0.68

0.0.67

0.0.66

0.0.65

0.0.63

0.0.62

0.0.61

0.0.60

0.0.59

0.0.58

0.0.57

0.0.56

0.0.55

0.0.54

0.0.53

0.0.52

0.0.51

0.0.50

0.0.49

0.0.48

0.0.46

0.0.44

0.0.43

0.0.42

0.0.41

0.0.40

This version

0.0.38

0.0.37

0.0.36

0.0.35

0.0.34

0.0.33

0.0.32

0.0.31

0.0.30

0.0.29

0.0.28

0.0.27

0.0.26

0.0.25

0.0.24

0.0.23

0.0.22

0.0.21

0.0.20

0.0.19

0.0.18

0.0.17

0.0.16

0.0.15

0.0.14

0.0.12

0.0.10

0.0.9

0.0.8

0.0.6

0.0.5

0.0.4

0.0.3

0.0.2

0.0.1

Download files

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

Source Distribution

metacontroller_pytorch-0.0.38.tar.gz (336.8 kB view details)

Uploaded Source

Built Distribution

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

metacontroller_pytorch-0.0.38-py3-none-any.whl (13.7 kB view details)

Uploaded Python 3

File details

Details for the file metacontroller_pytorch-0.0.38.tar.gz.

File metadata

  • Download URL: metacontroller_pytorch-0.0.38.tar.gz
  • Upload date:
  • Size: 336.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for metacontroller_pytorch-0.0.38.tar.gz
Algorithm Hash digest
SHA256 696f463d84881b999c615ac3215c9af6b37dfe21e6db41d4857e10a1e9c1d111
MD5 0a4836c7cda29c87199bc2f69633a29b
BLAKE2b-256 0bfed8f550333d013b17eb8b3003ec7d82ff709fcf05ed3b6d13266ba9d3ed59

See more details on using hashes here.

File details

Details for the file metacontroller_pytorch-0.0.38-py3-none-any.whl.

File metadata

File hashes

Hashes for metacontroller_pytorch-0.0.38-py3-none-any.whl
Algorithm Hash digest
SHA256 4a6281b9186475060e5e88afddea24e8177c67f9173c91f35ef427b539ad43a8
MD5 ae6448be47ce8eec4e2863b8b61efc8d
BLAKE2b-256 99789d898e1013e9155aec98492a5d31a9bc385f75443186b6721fc5d542c13c

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