atropos/environments/hack0
2025-05-18 13:41:01 -07:00
..
.python-version uv init 2025-05-18 12:48:21 -07:00
__init__.py initialized with grpo 2025-05-18 13:41:01 -07:00
grpo.py initialized with grpo 2025-05-18 13:41:01 -07:00
GRPO_README.md initialized with grpo 2025-05-18 13:41:01 -07:00
main.py uv init 2025-05-18 12:48:21 -07:00
pyproject.toml uv init 2025-05-18 12:48:21 -07:00
README.md init hackaton 2025-05-18 12:43:28 -07:00
requirements.txt initialized with grpo 2025-05-18 13:41:01 -07:00

Readme

a link to a 1 minute youtube video an explanation of your env design and motivation quickstart docs a link to a public wandb run from process and explanations of added metrics additional details about your env, e.g. reward hacking