diff --git a/README.md b/README.md index 036964c..82ab939 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,7 @@ To pre-process the Atari-HEAD data run [Preprocess_AtariHEAD.ipynb](Preprocess_A ## Intention-based Hierarchical RL Agent The Int-HRL agent is based on the hierarchically guided Imitation Learning method (hg-DAgger/Q), where we adapted code from [https://github.com/hoangminhle/hierarchical_IL_RL](https://github.com/hoangminhle/hierarchical_IL_RL)
-![results](supplementary/results_updated.pdf) +![results](supplementary/results_updated.png) Due to the novel sub-goal extraction pipeline, our agent does not require experts during training and is more than three times more sample efficient compared to hg-DAgger/Q.
diff --git a/supplementary/results_updated.pdf b/supplementary/results_updated.pdf deleted file mode 100644 index ec43ec7..0000000 Binary files a/supplementary/results_updated.pdf and /dev/null differ diff --git a/supplementary/results_updated.png b/supplementary/results_updated.png new file mode 100644 index 0000000..ca6fbd5 Binary files /dev/null and b/supplementary/results_updated.png differ