survival-rl

Survival RL (wip)

Explorations into an application of survival analysis to RL, proposed by Tiofack et al. earlier this year

Citations

@inproceedings{Tiofack2026SVL,
    title     = {SVL: Goal-Conditioned Reinforcement Learning as Survival Learning},
    author    = {Franki Nguimatsia Tiofack and Fabian Schramm and Th{\'e}otime Le Hellard and Justin Carpentier},
    booktitle = {International Conference on Machine Learning (ICML)},
    year      = {2026},
    url       = {https://arxiv.org/abs/2604.17551}
}

@article{Tiofack2026SRL,
    title   = {Survival Reinforcement Learning: Toward Scalable Self-Supervised RL},
    author  = {Franki Nguimatsia-Tiofack and Fabian Schramm and Th{\'e}otime Le Hellard and Justin Carpentier},
    journal = {arXiv preprint arXiv:2605.31273},
    year    = {2026},
    note    = {19th European Workshop on Reinforcement Learning (EWRL), Oral},
    url     = {https://arxiv.org/abs/2605.31273}
}

Metadata

Release files for survival-rl 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for survival-rl 0.0.1
File	Size	Uploaded
survival_rl-0.0.1.tar.gz	5.5 kB	Sep 28, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for survival-rl 0.0.1
File	Interpreter	ABI	Platform	Reset
survival_rl-0.0.1-py3-none-any.whl 4.7 kB Sep 28, 2026	Python 3	none	any	Details

Total release size: 10.2 kB

Release files / survival_rl-0.0.1.tar.gz

Download URL	survival_rl-0.0.1.tar.gz
Size	5.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`b4bdb1daf5fa21a7b305ced3af31273da9110c1b9536be901d4a9a5c974117c2`
BLAKE2b-256 checksum How to use checksums	`717bb54e51dfcf9c89e8545b6451c50d966f0f0b87d2d7b5d15d7c4816279830`
Upload date	Sep 28, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.17`

Release files / survival_rl-0.0.1-py3-none-any.whl

Download URL	survival_rl-0.0.1-py3-none-any.whl
Size	4.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0bf57e2ed53336754622528b213a88aba7d5ee4ae8e2a268feb871df17a26b7c`
BLAKE2b-256 checksum How to use checksums	`19fad7386d71e41c6c1ad611938555ae9385c86da2c029b12a57d8bf8eb123d2`
Upload date	Sep 28, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.8.17`