List your company

Model-free learning on Stochastic MDPs Bilinear or BE

2Regret T ExponentDu et al. (2021), Jin et al. (2021), Xie et al. (2023)
1.83.154.55.85Oct 10, 2025

Evaluation results

MethodLinks
Du et al. (2021), Jin et al. (2021), Xie et al. (2023)Exploration Mechanism=optimism, Estimation Protocol=on-policy2025.102
Du et al. (2021), Jin et al. (2021), Xie et al. (2023)Exploration Mechanism=optimism, Estimation Protocol=off-policy2025.102
Dig-DECExploration Mechanism=information gain, Estimation Protocol=on-policy2025.102
Foster et al. (2023b)Exploration Mechanism=information gain + optimism, Estimation Protocol=on-policy2025.103
Foster et al. (2023b)Exploration Mechanism=information gain + optimism, Estimation Protocol=off-policy2025.105
Dig-DECExploration Mechanism=information gain, Estimation Protocol=off-policy2025.107