No project description provided
Reason this release was yanked:
we need to stabilize before starting a 0.1.x release
Project description
Craftax LM
A wrapper around the Craftax agent benchmark, for evaluating digital agents.
Leaderboard
Craftax-Classic
LM | Algorithm | Reward (% max) | Code |
---|---|---|---|
gpt-4o-mini | ReAct | 14.2 | CraftaxLM_Baselines |
33 |
Craftax-Full
LM | Algorithm | Reward (% max) | Code |
---|---|---|---|
gpt-4o-mini | ReAct | 01.2 | CraftaxLM_Baselines |
Dev Instructions
pyenv virtualenv craftax_env
poetry install
When in doubt
from jax import debug
...
debug.breakpoint()
📚 Citation
To learn more about Craftax, check out the paper website here. To cite the underlying Craftax environment, see:
@inproceedings{matthews2024craftax,
author={Michael Matthews and Michael Beukman and Benjamin Ellis and Mikayel Samvelyan and Matthew Jackson and Samuel Coward and Jakob Foerster},
title = {Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning},
booktitle = {International Conference on Machine Learning ({ICML})},
year = {2024}
}
To cite the Crafter benchmark, see:
@article{hafner2021crafter,
title={Benchmarking the Spectrum of Agent Capabilities},
author={Danijar Hafner},
year={2021},
journal={arXiv preprint arXiv:2109.06780},
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
craftaxlm-0.1.0.tar.gz
(25.5 kB
view hashes)
Built Distribution
craftaxlm-0.1.0-py3-none-any.whl
(31.7 kB
view hashes)
Close
Hashes for craftaxlm-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b725b25fbfe1f53598601ca130f9a2021aec14b3cf98fdd8ff8d27643197a669 |
|
MD5 | 88ff2ca9d2f3f5a1a9a1e6988e65ecf7 |
|
BLAKE2b-256 | 7d02af124728b7840dd34fe2c53e9c4f0b6f1fdad504e9ec58bde5cc5a8482a5 |