ResearchBenchmarksGoal-conditioned Reinforcement Learning on NavixGoal-conditioned Reinforcement Learning on NavixFollow99.5IQM (Success Rate)CPPO69.02876.93984.8592.761May 13, 2026Evaluation resultsMethodMethodLinksIQM (Success Rate)CPPONumber of tasks=4 task...Number of tasks=4 tasks, Action space=discrete, Agent type=single-agent2026.0599.5CDQNNumber of tasks=4 task...Number of tasks=4 tasks, Action space=discrete, Agent type=single-agent2026.0570.2