Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds - Data Supplement

This is the data supplement for Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds. This version corresponds to the latest round of human player data collection. avalon__agent_eval_worlds.tar.gz contains all the evaluation worlds on which agents are scored avalon__human_eval_worlds.tar.gz contains all the evaluation worlds on which humans are scored (same as agent worlds, just some minor visual differences e.g. the colors are slightly modified for human comfort) avalon__human_data.tar.gz contains all the metadata, actions, inputs, and observations for the human players avalon__human_scores.json contains the scores for the human players