List your company

ResearchFormerly WizWand

Tabular MDP

Benchmarks

TaskDatasetSOTA resultTrendResults

Policy bias reduction

3-state × 2-action tabular MDP

4.5Fast-only Bias

10

Unregularized Reinforcement Learning

Tabular MDP Finite State Action Spaces

1Sample Complexity

3

Entropy-Regularized Reinforcement Learning

Tabular MDP Finite State Action Spaces

1Sample Complexity

2

Regret minimization in Reinforcement Learning

Tabular MDP

3Cumulative Regret

1

Reinforcement Learning

Tabular MDP

0.5Sample Complexity

1