Deep Reinforcement Learning with an Unbounded Action Space

By Ji He, Jianshu Chen, Xiaodong He, Jianfeng Gao, Lihong Li, Li Deng, Mari Ostendorf. 2015

19 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

Coarse-to-Fine Question Answering for Long Documents (2016, background): “Reinforcement learning recently gained popularity in tasks such as co-reference resolution (Clark and Manning, 2016), information extraction (Narasimhan et al., 2016), semantic parsing (Andreas et al., 2016) and textual games (Narasimhan et al., 2015; He et al., 2016).”
WebNav: A New Large-Scale Task for Natural Language based Sequential Decision Making (2016, background): “These successes have stimulated researchers to apply a similar learning mechanism to language based tasks, such as multi-user dungeon (MUD) games (Narasimhan et al., 2015; He et al., 2015).”
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning (2018, methodology): “ 2014). Previous work on TBG used pre-trained embeddings directly for control (Kostka et al., 2017; Fulda et al., 2017). Other works combined pre-trained embeddings with neural networks. For example, He et al. (2015) proposed to use Bag Of Words features as an input to a neural network, learned sepa”
End-to-End Goal-Driven Web Navigation (2016, background): “These successes have stimulated researchers to apply a similar learning mechanism to language-based tasks, such as multi-user dungeon (MUD) games [9, 4].”
Deep Reinforcement Learning in Large Discrete Action Spaces (2015, background): “Recent work extends Deep Q-Networks to ‘unbounded’ action spaces (He et al., 2015), effectively generating action representations for any action the environment provides, and picking the action that provides the highest Q.”