Merge branch 'torchbeast_baselines' into 'master'

Improve Torchbeast Baseline Instructions

See merge request nethack/neurips-2021-the-nethack-challenge!13

README.md

@@ -127,7 +127,7 @@ To then submit your saved model, simply set the `AGENT` in
 `submission config` to be `TorchBeastAgent`, and modify the 
 `agent/torchbeast_agent.py` to point to your saved directory.
 
-You can now test your saved model with `python test_baseline.py`
+You can now test your saved model with `python test_submission.py`
 
 **How can I get going with a completely new model?**
 

docs/SUBMISSION.md

@@ -15,6 +15,12 @@ You can modify the existing `rollout.py` OR copy it (to say `your_code.py`) and
 Before you submit make sure that you have saved your models, which are needed by your inference code.
 In case your files are larger in size you can use `git-lfs` to upload them. More details [here](https://discourse.aicrowd.com/t/how-to-upload-large-files-size-to-your-submission/2304).
 
+## Testing your model locally
+
+The best way to test your model is to run your submission locally.
+
+You can do this naively by simply running `python rollout.py` or you can simulate the extra timeout wrappers that AIcrowd will implement by using `python test_submission.py`.
+
 ## How to submit a trained model!
 
 To make a submission, you will have to create a **private** repository on [https://gitlab.aicrowd.com/](https://gitlab.aicrowd.com/).

nethack_baselines/torchbeast/README.md

@@ -14,7 +14,7 @@ batching.
 
 ## Installation
 
-To get this running all you need to do is follow the TorchBeast installation instructions from the [TorchBeast repo](https://github.com/facebookresearch/torchbeast).
+To get this running you'll need to follow the TorchBeast installation instructions for PolyBeast from the [TorchBeast repo](https://github.com/facebookresearch/torchbeast#installing-polybeast).
 
 A Dockerfile is also provided with installation of Torchbeast.
 
@@ -45,10 +45,9 @@ NOTE: if you get a "Too many open files" error, try: `ulimit -Sn 10000`.
 
 ## Making a submission
 
-In the output directory of your trained model, you should find two files, `checkpoint.tar` and `config.yaml`. Add both of them to your submission repo. Then change the `MODEL_DIR` variable in `agents/torchbeast_agent.py` to point to the directory where these files are located.
-
-After that, follow [these instructions](https://gitlab.aicrowd.com/roberta_raileanu/neurips-2021-nethack-starter-kit/-/blob/master/docs/SUBMISSION.md) to submit your model to AIcrowd!
+In the output directory of your trained model, you should find two files, `checkpoint.tar` and `config.yaml`. Add both of them to your submission repo. Then change the `MODEL_DIR` variable in `agents/torchbeast_agent.py` to point to the directory where these files are located. And finally, simply set the `AGENT` in `submission_config.py` to be 'TorchBeastAgent' so that your torchbeast agent variation is used for the submission.
 
+After that, follow [these instructions](/docs/SUBMISSION.md) to submit your model to AIcrowd!
 
 ## Repo Structure