Deep Reinforcement Learning with a Natural Language Action Space. (arXiv:1511.04636v5 [cs.AI] UPDATED)

This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to approximate the Q-function in reinforcement learning. We evaluate the DRRN on two popular text games, showing superior performance over other deep Q-learning architectures. Experiments with paraphrased action descriptions show that the model is extracting meaning rather than simply memorizing strings of text.

from cs.AI updates on arXiv.org http://ift.tt/1MiWHMd
via IFTTT