danijar / crafter

Benchmarking the Spectrum of Agent Capabilities

Home Page:https://danijar.com/crafter

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Running analysis scripts with jsonl files

roger-creus opened this issue · comments

Hi!

I am not being able to load the scripts in the analysis folder with the stored .jsonl files from the Recorder. I think the format of the saved files (line-separated dictionaries) is not the expected format for the analysis code. It is also not the same as the .json files that are stored in the scores/ folder. Am I missing something?

Thank you!

Hi, I think you need to use read_metrics.py first to convert them. Does that work?