Corpus ID: 210911499

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

@article{Ammanabrolu2020GraphCR,
  title={Graph Constrained Reinforcement Learning for Natural Language Action Spaces},
  author={Prithviraj Ammanabrolu and M. Hausknecht},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.08837}
}
Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in combinatorially-large text-based action spaces. We present KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based… Expand
20 Citations
LANGUAGE ACTION VALUE ESTIMATES
  • Highly Influenced
How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds
  • 4
  • PDF
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
  • 3
  • Highly Influenced
  • PDF
Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games
  • 15
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
  • 12
  • Highly Influenced
  • PDF
Keep CALM and Explore: Language Models for Action Generation in Text-based Games
  • 1
  • PDF
How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents
  • 2
  • PDF
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
  • 2
  • Highly Influenced
  • PDF
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
  • Highly Influenced
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 23 REFERENCES
Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
  • 40
  • PDF
Transfer in Deep Reinforcement Learning Using Knowledge Graphs
  • 15
  • PDF
Using reinforcement learning to learn how to play text-based games
  • 10
  • PDF
Language Understanding for Text-based Games using Deep Reinforcement Learning
  • 226
  • Highly Influential
  • PDF
TextWorld: A Learning Environment for Text-based Games
  • 89
  • PDF
Deep Reinforcement Learning with a Natural Language Action Space
  • 114
  • PDF
Interactive Fiction Games: A Colossal Adventure
  • 20
  • PDF
What Can You Do with a Rock? Affordance Extraction via Word Embeddings
  • 60
  • PDF
Toward Automated Quest Generation in Text-Adventure Games
  • 5
  • PDF
...
1
2
3
...