Share your thoughts, 1 month free Claude Pro on usSee more

Probability of Correct Selection on Stochastic Gridworld (S=16, A=4)

100PCS

LazyGradient

Updated 1mo ago

Evaluation Results

Method	Links
LazyGradient 2026.05		100
LazyGradient 2026.05		100
QOCBA 2026.05		92
QOCBA 2026.05		92
LazyGradient 2026.05		92
LazyGradient 2026.05		78
QOCBA 2026.05		70
PSRL 2026.05		56
QOCBA 2026.05		46
PSRL 2026.05		38
Actor-Critic 2026.05		26
PSRL 2026.05		18
Q-Learning 2026.05		16
PPO 2026.05		16
Q-Learning 2026.05		12
PPO 2026.05		10
Actor-Critic 2026.05		8
Q-Learning 2026.05		4
TRPO 2026.05		4
Q-Learning 2026.05		2
Actor-Critic 2026.05		2
Actor-Critic 2026.05		2
PSRL 2026.05		2
PPO 2026.05		0
PPO 2026.05		0
TRPO 2026.05		0
TRPO 2026.05		0
TRPO 2026.05		0