google-deepmind / google-deepmind/zipfian_environments

Reproduce Results

Open
#2 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
28
Forks
1
PR merge metrics
No merged PRs in 30d

Description

I tried training IMPALA on gridworld using the implementation from [torchbeast](https://github.com/facebookresearch/torchbeast). However, the results (uniform + uniform rare accuracy) I'm getting are not exactly matching the results in paper. Could you please share the implementation of IMPALA that was used in the paper.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.