List your company

Sequential Decision Making on Sokoban (val)

60.4Success RateEVPO
12.0424.59537.1549.705Apr 21, 2026

Evaluation results

MethodLinks
EVPOBackbone=Qwen2.5-3B-Instruct2026.0460.4
StarPO-SBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-based2026.0445.5
PPOBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-based2026.0431.4
DAPOBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-free2026.0416.2
GRPOBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-free2026.0415.6
Base LLMBackbone=Qwen2.5-3B-Instruct, Method Category=None2026.0413.9