ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Paper
•
2601.06487
•
Published
•
49
wei liu
qingww
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
9 days ago
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Organizations
None yet
upvoted
a
paper
9 days ago