Running
Repro: ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
🎯
Explore experiment logs, traces, and collaborate with an AI agent
👋 Open to Work
Laxmi Tiwari
laxuu
AI & ML interests
Agentic AI, RL, MARL
Recent Activity
published a Space about 24 hours ago
ICML-2026-agent-repro/ArenaRL published a Space about 24 hours ago
ICML-2026-agent-repro/ArenaRL_Scaling_RL_for_Open-Ended_Agents_via_Tournament-based_Relative_Ranking updated a Space 1 day ago
laxuu/arenarl-icml2026Organizations
