Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning

Autor:	Asadi, Kavosh, Cater, Evan, Misra, Dipendra, Littman, Michael L.
Rok vydání:	2018
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Learning a generative model is a key component of model-based reinforcement learning. Though learning a good model in the tabular setting is a simple task, learning a useful model in the approximate setting is challenging. In this context, an important question is the loss function used for model learning as varying the loss function can have a remarkable impact on effectiveness of planning. Recently Farahmand et al. (2017) proposed a value-aware model learning (VAML) objective that captures the structure of value function during model learning. Using tools from Asadi et al. (2018), we show that minimizing the VAML objective is in fact equivalent to minimizing the Wasserstein metric. This equivalence improves our understanding of value-aware models, and also creates a theoretical foundation for applications of Wasserstein in model-based reinforcement~learning. Comment: Accepted at the FAIM workshop "Prediction and Generative Modeling in Reinforcement Learning", Stockholm, Sweden, 2018
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1806.01265 Zobrazit plný text záznamu View this record from Arxiv