An environment for reproducing dominance hierarchies in RL agents
Project description
Chicken Coop
Supports Python 3.11.
Usage instructions:
# Set up virtualenv if needed:
python -m venv chicken-coop-env
source chicken-coop-env/bin/activate
# Install Chicken Coop:
pip install chicken-coop
# Run tests:
pytest
# Basic run:
python -m chicken_coop run
# Main run used in the paper:
python -m chicken_coop run --moniker paper-run --use-tune --n-tune-samples 300
# Transplant a visitor population into a resident population:
python -m chicken_coop transplant --moniker paper-transplant \
--visitor-trek ~/.chicken_coop/<YOUR_PREVIOUS_RUN>
# Ablate opponent perception accuracy:
python -m chicken_coop run --moniker paper-ablate-observation --use-tune --n-tune-samples 10 \
--observation-accuracy 0.0 \
--observation-accuracy 0.1 \
--observation-accuracy 0.2 \
--observation-accuracy 0.3 \
--observation-accuracy 0.4 \
--observation-accuracy 0.5 \
--observation-accuracy 0.6 \
--observation-accuracy 0.7 \
--observation-accuracy 0.8 \
--observation-accuracy 0.9 \
--observation-accuracy 1.0
# Investigate non-linearity:
python -m chicken_coop run --moniker paper-cycles --use-tune --n-tune-samples 30 --n-agents 12 \
--learning-rate 3e-05