Graph Constrained Reinforcement Learning for Natural Language Action Spaces
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 action space. We contend that the dual uses of the knowledge graph to reason about game state and to constrain natural language generation are the keys to scalable exploration of combinatorially large natural language actions. Results across a wide variety of IF games show that KG-A2C outperforms current IF agents despite the exponential increase in action space size.
Code (1)
Tasks
Action GenerationNatural Language Understandingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Text GenerationSimilar Papers 제목 키워드 기반
Normalized Cut with Reinforcement Learning in Constrained Action Space
Reinforcement Learning (RL) has emerged as an important paradigm to solve combinatorial optimization problems primarily due to its ability to learn heuristics that can generalize across problem instances. However, integr…
Combinatorial Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Training a Constrained Natural Media Painting Agent using Reinforcement Learning
We present a novel approach to train a natural media painting using reinforcement learning. Given a reference image, our formulation is based on stroke-based rendering that imitates human drawing and can be learned fro…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary
Enabling humanoid robots to follow free-form natural language commands is a critical step toward seamless human-robot interaction and general-purpose embodied AI. However, existing methods remain limited, often constrain…
Reinforcement LearningPlaying Text-Adventure Games with Graph-Based Deep Reinforcement Learning
Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture tha…
Deep Reinforcement LearningEfficient ExplorationQuestion Answeringreinforcement-learning+3Inherently Explainable Reinforcement Learning in Natural Language
We focus on the task of creating a reinforcement learning agent that is inherently explainable -- with the ability to produce immediate local explanations by thinking out loud while performing a task and analyzing entire…
Graph Attentionreinforcement-learningReinforcement LearningReinforcement Learning (RL)