firstbacksecondback
3 Results
|
Poster
|
Tue 14:00 |
Reinforcement Learning with Logarithmic Regret and Policy Switches Grigoris Velegkas · Zhuoran Yang · Amin Karbasi |
|
|
Poster
|
Tue 9:00 |
Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design Andrew Wagenmaker · Kevin Jamieson |
|
|
Poster
|
Thu 14:00 |
Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space Jonatha Anselmi · Bruno Gaujal · Louis-Sébastien Rebuffi |