Robotic Manipulation on Simulation pick-up-nut-from-peg
25Success RateLEAGUE sparse agent vs Reward Machine
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LEAGUE sparse agent vs Reward MachineEvaluation Protocol=Wilcoxon signed-rank test, Agent Architecture=PPO, Max Episode Length=1002026.03 | 25 | 12.5 | |
| Reward Machine vs LLM-Guided Subgoal agentEvaluation Protocol=Wilcoxon signed-rank test, Agent Architecture=PPO, Max Episode Length=1002026.03 | 1.07 | 1.07 | |
| LEAGUE sparse agent vs LLM-Guided Subgoal agentEvaluation Protocol=Wilcoxon signed-rank test, Agent Architecture=PPO, Max Episode Length=1002026.03 | 0.1 | 0.1 |