Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
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.
Code (2)
Tasks
Common Sense ReasoningCommonsense Reasoning for RLDecision MakingReinforcement Learning (RL)Sequential Decision Makingtext-based gamesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Approaches
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 gamesEnhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
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
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 gamesSituated Language Learning via Interactive Narratives
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 MakingWordCraft: An Environment for Benchmarking Commonsense Agents
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