Compact parametric models for efficient sequential decision making in high-dimensional, uncertain domains

[摘要] (cont.) In support of this, we present a reinforcement learning (RL) algorithm where the use of a parametric model allows the algorithm to make close to optimal decisions on all but a number of samples that scales polynomially with the dimension, a significant improvement over most prior RL provably approximately optimal algorithms. We also show that parametric models can be used to reduce the computational complexity from an exponential to polynomial dependence on the state dimension in forward search partially observable MDP planning. Under mild conditions our new forward-search POMDP planner maintains prior optimality guarantees on the resulting decisions. We present experimental results on a robot navigation over varying terrain RL task and a large global driving POMDP planning simulation.

[发布机构] Massachusetts Institute of Technology