Multi-View Reinforcement Learning Article Swipe

PDF

Related Concepts

Reinforcement learning Computer science Variety (cybernetics) Markov decision process Sample complexity Artificial intelligence Partially observable Markov decision process Sample (material) Observable Markov process Transfer of learning Machine learning Markov chain Markov model Mathematics Statistics Chemistry Quantum mechanics Physics Chromatography

Minne Li , Lisheng Wu , Jun Wang , Haitham Bou Ammar ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1910.08285 · OA: W2970162659

This paper is concerned with multi-view reinforcement learning (MVRL), which allows for decision making when agents share common dynamics but adhere to different observation models. We define the MVRL framework by extending partially observable Markov decision processes (POMDPs) to support more than one observation model and propose two solution methods through observation augmentation and cross-view policy transfer. We empirically evaluate our method and demonstrate its effectiveness in a variety of environments. Specifically, we show reductions in sample complexities and computational time for acquiring policies that handle multi-view environments.