paper-with-me

Papers

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

2020-01-23 · ICLR 2020 1 · Prithviraj Ammanabrolu, Matthew Hausknecht

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.

📄 PDF Abstract BibTeX arXiv:2001.08837

Code (1)

rajammanabrolu/KG-A2C 공식 구현 pytorch

Tasks

Action GenerationNatural Language Understandingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Text Generation

Similar Papers 제목 키워드 기반

Normalized Cut with Reinforcement Learning in Constrained Action Space

2025-05-20 · Qize Jiang, Linsey Pang, Alice Gatti, Mahima Aggarwal 외

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

2019-09-25 · Biao Jia, Jonathan Brandt, Radomir Mech, Ning Xu 외

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

2025-11-28 · Zhirui Liu, Kaiyang Ji, Ke Yang, Yahao Fan 외 arxiv

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 Learning

Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning

2018-12-04 · NAACL 2019 6 · Prithviraj Ammanabrolu, Mark O. Riedl

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+3

Inherently Explainable Reinforcement Learning in Natural Language

2021-12-16 · Xiangyu Peng, Mark O. Riedl, Prithviraj Ammanabrolu

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)