Published June 16, 2022
| Version 0.4.0
Dataset
Open
Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds - Data Supplement
Description
This is the data supplement for Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds.
- avalon__eval_worlds.zip contains all of the evaluation worlds on which agents are scored
- avalon__human_data.zip contains all the metadata, actions, inputs, observations, and scores for the human players
Notes
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)