Sequential Decision Making on FrozenLake (val)
68.4Success RateEVPO
Evaluation results
| Method | Links | |
|---|---|---|
| EVPOBackbone=Qwen2.5-3B-Instruct2026.04 | 68.4 | |
| PPOBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-based2026.04 | 61.1 | |
| StarPO-SBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-based2026.04 | 35.9 | |
| GRPOBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-free2026.04 | 23.4 | |
| DAPOBackbone=Qwen2.5-3B-Instruct, Method Category=Critic-free2026.04 | 20.7 | |
| Base LLMBackbone=Qwen2.5-3B-Instruct, Method Category=None2026.04 | 13.3 |