Towards Better Interpretability in Deep Q-Networks
نویسندگان
چکیده
منابع مشابه
Interpretability in Robinson's Q
Edward Nelson published in 1986 a book defending an extreme formalist view of mathematics according to which there is an impassable barrier in the totality of exponentiation. On the positive side, Nelson embarks on a program of investigating how much mathematics can be interpreted in Raphael Robinson’s theory of arithmetic Q. In the shadow of this program, some very nice logical investigations ...
متن کاملDeep Abstract Q-Networks
We examine the problem of learning and planning on highdimensional domains with long horizons and sparse rewards. Recent approaches have shown great successes in many Atari 2600 domains. However, domains with long horizons and sparse rewards, such as Montezuma’s Revenge and Venture, remain challenging for existing methods. Methods using abstraction (Dietterich 2000; Sutton, Precup, and Singh 19...
متن کاملTowards better performance with heterogeneous training data in acoustic modeling using deep neural networks
Modeling heterogeneous data sources remains a fundamental challenge of acoustic modeling in speech recognition. We call this the multi-condition problem because the speech data come from many different conditions. In this paper, we introduce the fundamental confusability problem in multi-condition learning, then discuss the problem formalization, the taxonomy, and the architectures for multi-co...
متن کاملEfficient Exploration through Bayesian Deep Q-Networks
We propose Bayesian Deep Q-Network (BDQN), a practical Thompson sampling based Reinforcement Learning (RL) Algorithm. Thompson sampling allows for targeted exploration in high dimensions through posterior sampling but is usually computationally expensive. We address this limitation by introducing uncertainty only at the output layer of the network through a Bayesian Linear Regression (BLR) mode...
متن کاملDeep Q-Learning With Recurrent Neural Networks
Deep reinforcement learning models have proven to be successful at learning control policies image inputs. They have, however, struggled with learning policies that require longer term information. Recurrent neural network architectures have been used in tasks dealing with longer term dependencies between data points. We investigate these architectures to overcome the difficulties arising from ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33014561