paper-with-me

Papers

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

2020-10-08 · Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla, Sadhana Kumaravel, Gerald Tesauro, Kartik Talamadupula, Mrinmaya Sachan, Murray Campbell

Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of infusing RL agents with commonsense knowledge. Such knowledge would allow agents to efficiently act in the world by pruning out implausible actions, and to perform look-ahead planning to determine how current actions might affect future world states. We design a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances. We also introduce several baseline RL agents which track the sequential context and dynamically retrieve the relevant commonsense knowledge from ConceptNet. We show that agents which incorporate commonsense knowledge in TWC perform better, while acting more efficiently. We conduct user-studies to estimate human performance on TWC and show that there is ample room for future improvement.

📄 PDF Abstract BibTeX arXiv:2010.03790

Code (2)

IBM/commonsense-rl 공식 구현 pytorch
cognitiveailab/textworldexpress

Tasks

Common Sense ReasoningCommonsense Reasoning for RLDecision MakingReinforcement Learning (RL)Sequential Decision Makingtext-based games

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
BiGRU A Bidirectional GRU, or BiGRU, is a sequence processing model that consists of two GRUs. one taking the input in a forward…
GAT A Graph Attention Network (GAT) is a neural network architecture that operates on graph-structured data, leveraging masked self-attentional layers to address the shortcomings…

Similar Papers 제목 키워드 기반

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Approaches

2020-07-12 · Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Pushkar Shukla 외

Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine t…

Decision MakingReinforcement Learning (RL)Sequential Decision Makingtext-based games

Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge

2020-05-02 · Keerthiram Murugesan, Mattia Atzeni, Pushkar Shukla, Mrinmaya Sachan 외

In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

ScriptWorld: Text Based Environment For Learning Procedural Knowledge

2023-07-08 · Abhinav Joshi, Areeb Ahmad, Umang Pandey, Ashutosh Modi

Text-based games provide a framework for developing natural language understanding and commonsense knowledge about the world in reinforcement learning based agents. Existing text-based environments often rely on fictiona…

Language ModelingLanguage ModellingNatural Language Understandingtext-based games

Situated Language Learning via Interactive Narratives

2021-03-18 · Prithviraj Ammanabrolu, Mark O. Riedl

This paper provides a roadmap that explores the question of how to imbue learning agents with the ability to understand and generate contextually relevant natural language in service of achieving a goal. We hypothesize t…

Decision MakingSequential Decision Making

WordCraft: An Environment for Benchmarking Commonsense Agents

2020-07-17 · ICML Workshop LaReL 2020 7 · Minqi Jiang, Jelena Luketina, Nantas Nardelli, Pasquale Minervini 외

The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpora and integrate it with reinforcement l…

BenchmarkingKnowledge GraphsReinforcement Learning (RL)Representation Learning