Implementations for imitation learning / IRL algorithms in RLLAB

Contains:

• GAIL
• Guided Cost Learning, GAN formulation
• Adversarial IRL
• Tabular MaxCausalEnt IRL

This library requires:

• rllab (https://github.com/openai/rllab)
• Tensorflow

Running the Pendulum-v0 gym environment:

1. Collect expert data

python scripts/pendulum_data_collect.py

You should get an "AverageReturn" of around -100 to -150

2. Run imitation learning

python scripts/pendulum_gcl.py

The "OriginalTaskAverageReturn" should reach around -100 to -150