2 problems

0 votes0 replies0 views
Smooth-transition conjecture for episodic VI-LCB
Smooth-transition conjecture. If $1 \leq C^\pi \leq 2$ , then
Conjectureopenepisodic-mdps imitation-learning offline-reinforcement-learningarXiv posted 2 days ago
0 votes0 replies0 views
The longer-horizon data-volume conjecture in imitation learning
In an imitation-learning problem, let $n$ be the number of expert trajectories and $H$ their horizon, so that the expert dataset contains $nH$ state-action pairs. The observed phen…
Conjectureopenbehavior-cloning imitation-learning reinforcement-learningarXiv posted 2 days ago

Smooth-transition conjecture for episodic VI-LCB