Robotic Manipulation on Simulation pick-up-lid-from-pot
0.001Success Rate P-ValueLEAGUE sparse agent vs LLM-Guided Subgoal agent
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LEAGUE sparse agent vs LLM-Guided Subgoal agentEvaluation Protocol=Wilcoxon signed-rank test, Agent Architecture=PPO, Max Episode Length=1002026.03 | 0.001 | 0.001 | |
| LEAGUE sparse agent vs Reward MachineEvaluation Protocol=Wilcoxon signed-rank test, Agent Architecture=PPO, Max Episode Length=1002026.03 | 0.0156 | 0.0156 | |
| Reward Machine vs LLM-Guided Subgoal agentEvaluation Protocol=Wilcoxon signed-rank test, Agent Architecture=PPO, Max Episode Length=1002026.03 | 0.0313 | 0.0313 |