A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Abi Komanduru 1 Jean Honorio 2
Abstract problem can be embedded in LMDP, solutions to standard
MDP problems based on standard MDPs are guaranteed to
Inverse reinforcement learning (IRL) is the task of
generate the desired Bellman optimal policy given the true
finding a reward function that generates a ...


雷达卡




京公网安备 11010802022788号







