Multi-task Reinforcement Learning on ALFWorld
82Validation ScoreComplementary RL
Evaluation results
| Method | Links | |
|---|---|---|
| Complementary RLexperience_retrieval_at_test_time=true2026.03 | 82 | |
| Complementary RLexperience_retrieval_at_test_time=false2026.03 | 74 | |
| Baseline2026.03 | 72 | |
| Static Online Exp.experience_retrieval_at_test_time=true2026.03 | 69 | |
| Static Online Exp.experience_retrieval_at_test_time=false2026.03 | 64 | |
| Exp. Only2026.03 | 13 |