Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes

Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes
复制标题

DOI:
10.1609/aaai.v31i1.11065
复制
发表时间:
2017-02
期刊:
Advances in neural information processing systems
影响因子:
--
通讯作者:
Taylor W. Killian;G. Konidaris;F. Doshi-Velez
Taylor W. Killian;G. Konidaris;F. Doshi-Velez
中科院分区:
其他
文献类型:
--
作者:
Taylor W. Killian;G. Konidaris;F. Doshi-Velez

文献摘要

被引文献

相似文献

提出了一种新的隐参数马尔可夫决策过程(HIP-MDP),这是一个利用低维潜在嵌入对相关任务族进行建模的框架。我们的新框架正确地模拟了潜在参数和状态空间中的联合不确定性。我们还用贝叶斯神经网络取代了原来基于高斯过程的模型,使推理具有更高的可扩展性。因此,我们将HIP-MDP的范围扩展到更高维度和更复杂的动力学应用。
We introduce a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP), a framework for modeling families of related tasks using low-dimensional latent embeddings. Our new framework correctly models the joint uncertainty in the latent parameters and the state space. We also replace the original Gaussian Process-based model with a Bayesian Neural Network, enabling more scalable inference. Thus, we expand the scope of the HiP-MDP to applications with higher dimensions and more complex dynamics.