Imitation learning algorithms (with PPO [1]):
python main.py --imitation [AIRL|BC|DRIL|FAIRL|GAIL|GMMIL|PUGAIL|RED]
Options include:
- State-only imitation learning:
--state-only - Absorbing state indicator [12]:
--absorbing - R1 gradient regularisation [13]:
--r1-reg-coeff 1(default)
PPO
| Train | Test |
|---|---|
 |
 |
AIRL
| Train | Test |
|---|---|
 |
 |
BC
| Train | Test |
|---|---|
 |
|
DRIL
| Train | Test |
|---|---|
 |
 |
FAIRL
| Train | Test |
|---|---|
 |
 |
GAIL
| Train | Test |
|---|---|
 |
 |
GMMIL
| Train | Test |
|---|---|
 |
 |
nn-PUGAIL
| Train | Test |
|---|---|
 |
 |
RED
| Train | Test |
|---|---|
 |
 |
If you find this work useful and would like to cite it, the following would be appropriate:
@misc{arulkumaran2020pragmatic,
author = {Arulkumaran, Kai},
title = {A Pragmatic Look at Deep Imitation Learning},
url = {https://github.com/Kaixhin/imitation-learning},
year = {2020}
}
[1] Proximal Policy Optimization Algorithms
[2] Adversarial Behavioral Cloning
[3] Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
[4] Efficient Training of Artificial Neural Networks for Autonomous Navigation
[5] Disagreement-Regularized Imitation Learning
[6] A Divergence Minimization Perspective on Imitation Learning Methods
[7] Generative Adversarial Imitation Learning
[8] Imitation Learning via Kernel Mean Embedding
[9] Positive-Unlabeled Reward Learning
[10] Primal Wasserstein Imitation Learning
[11] Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation
[12] Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
[13] Which Training Methods for GANs do actually Converge?