Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowledge -- like commonsense knowledge -- to improve the efficiency of RL agents for TBGs; and to resemble human-like decision-making skills. In this paper, we posit that to act efficiently in TBGs, an agent must be able to track the state of the game while retrieving and using relevant commonsense knowledge. Thus, we propose an agent for TBGs that induces a graph representation of the game state and jointly grounds it with a graph of commonsense knowledge from ConceptNet. This combination is achieved through bidirectional knowledge graph attention between the two symbolic representations. We show that agents that incorporate commonsense into the game state graph outperform baseline agents.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingGraph Attentionreinforcement-learningReinforcement Learning (RL)text-based gamesSimilar Papers 제목 키워드 기반
Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowl…
Graph AttentionReinforcement Learning (RL)text-based gamesLOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning
Commonsense reasoning often involves evaluating multiple plausible interpretations rather than selecting a single atomic answer, yet most benchmarks rely on single-label evaluation, obscuring whether statements are joint…
ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation
This paper describes our system for SemEval-2020 Task 4: Commonsense Validation and Explanation (Wang et al., 2020). We propose a novel Knowledge-enhanced Graph Attention Network (KEGAT) architecture for this task, lever…
Data AugmentationGraph AttentionKM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation
We present Knowledge Enhanced Multimodal BART (KM-BART), which is a Transformer-based sequence-to-sequence model capable of reasoning about commonsense knowledge from multimodal inputs of images and texts. We adapt the g…
Knowledge GraphsLanguage ModelingLanguage ModellingLarge Language ModelText-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 t…
Common Sense ReasoningCommonsense Reasoning for RLDecision MakingReinforcement Learning (RL)+2