4 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
Conjectured bound for the second error term in moderate-coverage episodic VI-LCB
Second-term bound conjecture.
Conjectureopenepisodic-mdps offline-reinforcement-learning sample-complexityarXiv posted 2 days ago
0 votes0 replies0 views
Adaptive optimality conjecture for VI-LCB in offline Markov decision processes
VI-LCB optimality conjecture. VI-LCB is optimal for all ranges of $C^\star$ .
Conjectureopenconfidence-bounds markov-decision-processes offline-reinforcement-learningarXiv posted 2 days ago
0 votes0 replies0 views
Adaptive optimality conjecture for LCB in offline Markov decision processes
Adaptive optimality conjecture. The LCB approach, together with value iteration, is adaptively optimal for solving offline MDPs for all ranges of $C^\star$ .
Conjectureopenconfidence-bounds markov-decision-processes offline-reinforcement-learningarXiv posted 2 days ago

Smooth-transition conjecture for episodic VI-LCB