List your company

ResearchFormerly WizWand

MDP with Tucker rank

Benchmarks

TaskDatasetSOTA resultTrendResults

Regret Minimization

MDP with Tucker Rank (d, S, A) (theoretical)

—Primary metric

0

Regret Minimization

MDP with Tucker Rank (S, d, A) (theoretical)

—Primary metric

0

Regret Minimization

MDP with Tucker Rank (S, S, d) (theoretical)

—Primary metric

0

Transfer Reinforcement Learning

MDP with Tucker rank (S, d, A)

—Primary metric

0