Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environments
Not on the map. Why?
Abstract (arXiv)
Text-based simulated environments have proven to be a valid testbed for machine learning approaches. The process of affordance extraction can be used to generate possible actions for interaction within such an environment. In this paper the capabilities and challenges for utilizing external knowledge databases (in particular ConceptNet) in the process of affordance extraction are studied. An algorithm for automated affordance extraction is introduced and evaluated on the Interactive Fiction (IF) platforms TextWorld and Jericho. For this purpose, the collected affordances are translated into text commands for IF agents. To probe the quality of the automated evaluation process, an additional human baseline study is conducted. The paper illustrates that, despite some challenges, external databases can in principle be used for affordance extraction. The paper concludes with recommendations for further modification and improvement of the process.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 1 Jul 2022.
Builds on
20 of 32 references.
References · 20
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
- 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
- 2019Interactive Fiction Games: A Colossal Adventurecited by 165
- 2020Graph Constrained Reinforcement Learning for Natural Language Action Spacescited by 80
- 2018Investigating Human Priors for Playing Video Gamescited by 39
- 2020What can I do here? A Theory of Affordances in Reinforcement Learningcited by 33
- 2020Exploration Based Language Learning for Text-Based Gamescited by 18
- 2019NAIL: A General Interactive Fiction Agentcited by 17
- 2019LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Gamescited by 17
- 2020Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledgecited by 16
- 2019Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fictioncited by 14
- 2017What can you do with a rock? Affordance extraction via word embeddingscited by 13
8 more
- 2019Comprehensible Context-driven Text Game Playingcited by 10
- 2020How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agentscited by 10
- 2019Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spacescited by 7
- 2018The Text-Based Adventure AI Competitioncited by 5
- 2018Towards Solving Text-based Games by Producing Adaptive Action Spacescited by 5
- 2019Building Dynamic Knowledge Graphs from Text-based Gamescited by 4
- 2018Affordance Extraction and Inference based on Semantic Role Labelingcited by 3
- 2018Baselines for Reinforcement Learning in Text Gamescited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.