Deep Reinforcement Learning with a Natural Language Action Space
arXiv:1511.04636
Abstract
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.
accepted by ACL 2016
References in corpus (3)
Cited by in corpus (13)
- Semi-supervised Deep Reinforcement Learning in Support of IoT and Smart City Services
- Counting to Explore and Generalize in Text-based Games
- An empirical investigation of the challenges of real-world reinforcement learning
- Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
- Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
- Keep CALM and Explore: Language Models for Action Generation in Text-based Games
- Language Expansion In Text-Based Games
- Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory
- Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control
- Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
- Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task
- Reinforcement Learning for Strategic Recommendations
- Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning