List your company
ResearchFormerly WizWand

Instruction Following on BabyAI Pickup

0.486Average Episodic RewardPoly-PPO w/ UCB
0.12720.220350.31350.40665Sep 29, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Poly-PPO w/ UCBRL Algorithm=Poly-PPO, Exploration Strategy (UCB)=UCB2025.090.48665.6
Poly-PPORL Algorithm=Poly-PPO, Exploration Strategy (UCB)=None2025.090.45263.2
REINFORCE w/ UCBRL Algorithm=REINFORCE, Exploration Strategy (UCB)=UCB2025.090.39156
PPORL Algorithm=PPO, Exploration Strategy (UCB)=None2025.090.28333.4
REINFORCERL Algorithm=REINFORCE, Exploration Strategy (UCB)=None2025.090.25939.8
PPO w/ UCBRL Algorithm=PPO, Exploration Strategy (UCB)=UCB2025.090.24327.8
Pretrained policyRL Algorithm=Pretrained policy, Exploration Strategy (UCB)=None2025.090.14121.4