Deep Reinforcement Learning with a Natural Language Action Space Deep Reinforcement Learning with a Natural Language Action Space
Paper summary TLDR; The authors train a DQN on text-based games. The main difference is that their Q-Value functions embeds the state (textual context) and action (text-based choice) separately and then takes the dot product between them. The authors call this a Deep Reinforcement Learning Relevance network. Basically, just a different Q function implementation. Empirically, the authors show that their network can learn to solve "Saving John" and "Machine of Death" text games.
arxiv.org
arxiv-sanity.com
scholar.google.com
Deep Reinforcement Learning with a Natural Language Action Space
Ji He and Jianshu Chen and Xiaodong He and Jianfeng Gao and Lihong Li and Li Deng and Mari Ostendorf
arXiv e-Print archive - 2015 via arXiv
Keywords: cs.AI, cs.CL, cs.LG

more

Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About