Skip to content

Commit

Permalink
Added the single agent PPO checkpoint
Browse files Browse the repository at this point in the history
  • Loading branch information
martinballa committed Dec 3, 2020
1 parent f6c4c79 commit 4539976
Show file tree
Hide file tree
Showing 10 changed files with 427 additions and 273 deletions.
2 changes: 1 addition & 1 deletion examples/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ We also provided non-notebook versions of these guides, which contain less expla
If you have any issues with running Malmo check the [FAQ](FAQ.md) as it might cover the issues.

## Baseline results
Single-agent PPO
**Single-agent PPO**

We trained PPO in single and multi-agent setups on the Mob chases tasks. The tensorboard learning curves are shown below from a run of 1 million agent-env interactions. The checkpoint is available in the ```examples/checkpoints/``` package.
![Single Agent PPO learning curves](imgs/PPO_single_agent_mobchase.png)
Expand Down
Empty file.
Binary file not shown.
Binary file not shown.
Binary file not shown.
7 changes: 7 additions & 0 deletions examples/checkpoints/PPO_malmo_single_agent/params.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
{
"env": "malmo",
"ignore_worker_failures": true,
"lr": 5e-05,
"num_gpus": 1,
"num_workers": 6
}
Binary file not shown.
210 changes: 210 additions & 0 deletions examples/checkpoints/PPO_malmo_single_agent/progress.csv

Large diffs are not rendered by default.

209 changes: 209 additions & 0 deletions examples/checkpoints/PPO_malmo_single_agent/result.json

Large diffs are not rendered by default.

272 changes: 0 additions & 272 deletions examples/notebooks/rllib_evaluate_checkpoint.ipynb

This file was deleted.

0 comments on commit 4539976

Please sign in to comment.