Contains PyTorch implementation of the BC, MM (WGAIL), and Replay Estimation algorithms.
To install dependencies, run:
conda env create -f env.yml
To train an expert, run:
python experts/train.py -e env_name
To train a learner, run:
python learners/train.py -a algo_name -e env_name -n num_runs
This package supports training via:
- Behavioral Cloning
- WGAIL
- Replay