Showing 2026Show all
2 papers · 1 filter
stat.ML2026
Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
Corentin Pla, Hugo Richard, Marc Abeille +1
We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of actions before deciding its…
stat.ML2026
Minimax PAC Bounds for Learning in Exogenous Contextual MDPs
Corentin Pla, Hugo Richard, Marc Abeille +1
We introduce a PAC framework in which the learner can access sampling oracles both before and at decision time. Sample complexity is measured by a pair , where is the le…