huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Arec Jamgochian
2022-03-04 05:19:26 +01:00
committed by GitHub
parent 597b9af5d4
commit 3ac9465997
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -20,7 +20,7 @@ The INTERACTION dataset contains a two folders which should be copied into a fol
- the contents of `maps` should be copied to `./InteractionSimulator/datasets/maps`
## Processing and saving expert demos
Once the repository has been set up, you need to generate two separate sets of expert demos for tracks 0-4. The first command generates true joint and individual states and actions, necessary for evaluating. The second command generates trajectory rollouts according to individual agent observations, which will be used in behavior cloning, along with gail/hail/shail discriminators.
Once the repository has been set up, you need to generate two separate sets of expert demos for tracks 0-4. The first command generates true joint and individual states and actions necessary for evaluating, saving them in `expert_data/`. The second command generates trajectory rollouts according to individual agent observations, which is later used as expert data for the learning models.
```
python -m src.expert --locs='[DR_USA_Roundabout_FT]' --tracks='[0,1,2,3,4]'
python -m intersimple-expert-rollout-setobs2 --tracks='[0,1,2,3,4]'
@@ -28,9 +28,9 @@ python -m intersimple-expert-rollout-setobs2 --tracks='[0,1,2,3,4]'
## Tuning hyperparameters and training finalized models
To tune models, we use `ray[tune]` grid searches. You can run see the commands we used to train in the top half of `train_models.sh`. After training the models, configurations get saved in `best_configs/`. However, we note some better performance manually at earlier epochs of training, so we adjusted our `best_configs` manually.
To tune models, we use `ray[tune]` grid searches. You can run see the commands we used to train in the top half of `train_models.sh`, as well as the hyperparameters we search over in `bc-experiment.py`, `gail-experiment.py`, and `shail-experiment.py`. After training the models, configurations get saved in `best_configs/` (the best SHAIL confg gets copied to a HAIL config, with the appropriate environment parameters changed for ablation). However, upon manual inspection of the training runs, we note some better performance than the automatically-set configs at earlier epochs, so we adjust the `best_configs` manually.
After the `best_configs/` are set, we rereun each configuration with multiple seeds, the commands to do so are in the bottom half of `train_models.sh`. This saves different policy files to `test_policies/`.
After the `best_configs/` are set, we rerun each configuration with multiple seeds. The commands to do so are in the bottom half of `train_models.sh`. This saves different learned policy files to `test_policies/`.
## Evaluating models