Commit 95b55ed1 authored by nilabha's avatar nilabha

update changes for IL README

parent c5fca9de
......@@ -70,12 +70,12 @@ We follow the below steps to generate our list of expert demonstration
* Now run the `saving_experiences.py` to generate the expert demonstrations in rllib format (`*.json`)
* Copy the generated experiences to the location `\tmp\flatland-out`
For the training process refer to the [training](#training) section.
#### Run Model with Expert Demonstrations
The **custom_loss_model** model file contains the code basis for all concepts needed for Imitation Loss implementation.
For the training process refer to the [training](#training) section.
### 📈 Results
Results for MARWIL and APEX based Imitation Learning
......@@ -99,6 +99,6 @@ The results show that a pure Imitation Learning can help push the mean completio
### 🌟 Credits
- [🐦 Nilabha Bhattacharya](nilabha.ext@aicrowd.com)
- [🐦 Jeremy Watson](jeremy@aicrowd.com)
- [🐦 Florian Laurent](florian@aicrowd.com)
\ No newline at end of file
- [Nilabha Bhattacharya](nilabha.ext@aicrowd.com)
- [Jeremy Watson](jeremy@aicrowd.com)
- [Florian Laurent](florian@aicrowd.com)
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment