Instruction Following on BabyAI Pickup
0.486Average Episodic RewardPoly-PPO w/ UCB
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Poly-PPO w/ UCBRL Algorithm=Poly-PPO, Exploration Strategy (UCB)=UCB2025.09 | 0.486 | 65.6 | |
| Poly-PPORL Algorithm=Poly-PPO, Exploration Strategy (UCB)=None2025.09 | 0.452 | 63.2 | |
| REINFORCE w/ UCBRL Algorithm=REINFORCE, Exploration Strategy (UCB)=UCB2025.09 | 0.391 | 56 | |
| PPORL Algorithm=PPO, Exploration Strategy (UCB)=None2025.09 | 0.283 | 33.4 | |
| REINFORCERL Algorithm=REINFORCE, Exploration Strategy (UCB)=None2025.09 | 0.259 | 39.8 | |
| PPO w/ UCBRL Algorithm=PPO, Exploration Strategy (UCB)=UCB2025.09 | 0.243 | 27.8 | |
| Pretrained policyRL Algorithm=Pretrained policy, Exploration Strategy (UCB)=None2025.09 | 0.141 | 21.4 |