Equivalence Between Wasserstein and Value-Aware Model-based Reinforcement Learning
arXiv: Learning, Volume abs/1806.01265, 2018.
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. Recently Farahmand et al. (2017) proposed a value-aware (VAML) objective that captures the structure of value functio...More
Full Text (Upload PDF)
PPT (Upload PPT)