Navigation on MiniGrid Four Rooms (val)
0.672Average Episodic RewardREINFORCE w/ UCB
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| REINFORCE w/ UCBRL Algorithm=REINFORCE, Exploration Strategy (UCB)=UCB2025.09 | 0.672 | 92.6 | |
| Poly-PPORL Algorithm=Poly-PPO, Exploration Strategy (UCB)=None2025.09 | 0.666 | 92.4 | |
| Poly-PPO w/ UCBRL Algorithm=Poly-PPO, Exploration Strategy (UCB)=UCB2025.09 | 0.653 | 91.8 | |
| REINFORCERL Algorithm=REINFORCE, Exploration Strategy (UCB)=None2025.09 | 0.639 | 89.6 | |
| PPORL Algorithm=PPO, Exploration Strategy (UCB)=None2025.09 | 0.618 | 89.2 | |
| PPO w/ UCBRL Algorithm=PPO, Exploration Strategy (UCB)=UCB2025.09 | 0.502 | 78.6 | |
| Pretrained policyRL Algorithm=Pretrained policy, Exploration Strategy (UCB)=None2025.09 | 0.469 | 70.4 |