2019/05/23 by Chen Tessler, Tessler, Chen, Tom Zahavy +8 · 2 citations
Computer Science · #Artificial Intelligence in Games #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #cs.LG
paper · pdf · doi:10.48550/arxiv.1905.09700
Under review at IJCAI 2020
openalex publication_date 2019/05/23 · openalex created_date 2019/05/29 · arxiv created 2020/02/09 · arxiv updated 2020/02/11 · openalex updated_date 2026/07/28
We propose a computationally efficient algorithm that combines compressed sensing with imitation learning to solve text-based games with combinatorial action spaces. Specifically, we introduce a new compressed sensing algorithm, named IK-OMP, which can be seen as an extension to the Orthogonal Matching Pursuit (OMP). We incorporate IK-OMP into a supervised imitation learning setting and show that the combined approach (Sparse Imitation Learning, Sparse-IL) solves the entire text-based game of Zork1 with an action space of approximately 10 million actions given both perfect and noisy demonstrations.