@unpublished{Arulkumaran:2016,
author = {Arulkumaran, K and Dilokthanakul, N and Shanahan, M and Bharath, AA},
publisher = {IJCAI},
title = {Classifying options for deep reinforcement learning},
url = {http://arxiv.org/abs/1604.08153v1},
year = {2016}
}

Download

TY  - UNPB
AB  - Deep reinforcement learning is the learning of multiple levels ofhierarchical representations for reinforcement learning. Hierarchicalreinforcement learning focuses on temporal abstractions in planning andlearning, allowing temporally-extended actions to be transferred between tasks.In this paper we combine one method for hierarchical reinforcement learning -the options framework - with deep Q-networks (DQNs) through the use ofdifferent "option heads" on the policy network, and a supervisory network forchoosing between the different options. We show that in a domain where we haveprior knowledge of the mapping between states and options, our augmented DQNachieves a policy competitive with that of a standard DQN, but with much lowersample complexity. This is achieved through a straightforward architecturaladjustment to the DQN, as well as an additional supervised neural network.
AU  - Arulkumaran,K
AU  - Dilokthanakul,N
AU  - Shanahan,M
AU  - Bharath,AA
PB  - IJCAI
PY  - 2016///
TI  - Classifying options for deep reinforcement learning
UR  - http://arxiv.org/abs/1604.08153v1
UR  - http://hdl.handle.net/10044/1/32327
ER  - 

Download