mlsanityData to 7 Oct 2026

How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds

arXiv 2010.00685 ↗First posted 1 Oct 2020cs.CL cs.AIcited by 35

Not on the map. Why?

Abstract (arXiv)

We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019) -- a large-scale crowd-sourced fantasy text-game -- with a dataset of quests. These contain natural language motivations paired with in-game goals and human demonstrations; completing a quest might require dialogue or actions (or both). We introduce a reinforcement learning system that (1) incorporates large-scale language modeling-based and commonsense reasoning-based pre-training to imbue the agent with relevant priors; and (2) leverages a factorized action space of action commands and dialogue, balancing between the two. We conduct zero-shot evaluations using held-out human expert demonstrations, showing that our agents are able to act consistently and talk naturally with respect to their motivations.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 6; 2024: 6; 2025: 0; 2026: 1.

35 papers.

Sort:

By area:

  1. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  2. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  3. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  4. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
  5. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 88
  6. 2022A data-driven approach for learning to control computerscited by 87
  7. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  8. 2022Dungeons and Dragons as a Dialog Challenge for Artificial Intelligencecited by 35
  9. 2022Aligning to Social Norms and Values in Interactive Narrativescited by 32
  10. 2022I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragonscited by 22
  11. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17
  12. 2021Towards Socially Intelligent Agents with Mental State Transition and Human Utilitycited by 14
23 more
  1. 2021A Survey of Text Games for Reinforcement Learning informed by Natural Languagecited by 14
  2. 2021Hey AI, Can You Solve Complex Tasks by Talking to Agents?cited by 13
  3. 2022TextWorldExpress: Simulating Text Games at One Million Steps Per Secondcited by 12
  4. 2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
  5. 2023LaMPP: Language Models as Probabilistic Priors for Perception and Actioncited by 11
  6. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  7. 2022Behavior Cloned Transformers are Neurosymbolic Reasonerscited by 10
  8. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  9. 2024CHIRON: Rich Character Representations in Long-Form Narrativescited by 9
  10. 2021SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agentscited by 7
  11. 2023Story Shaping: Teaching Agents Human-like Behavior with Storiescited by 7
  12. 2022Language Modeling with Latent Situationscited by 6
  13. 2023Thespian: Multi-Character Text Role-Playing Game Agentscited by 6
  14. 2023The Open-domain Paradox for Chatbots: Common Ground as the Basis for Human-like Dialoguecited by 4
  15. 2021Situated Language Learning via Interactive Narrativescited by 2
  16. 2024Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domaincited by 2
  17. 2024A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worldscited by 2
  18. 2024SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Eventscited by 2
  19. 2021SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agentscited by 1
  20. 2022CausalDialogue: Modeling Utterance-level Causality in Conversationscited by 1
  21. 2024Safe Guard: an LLM-agent for Real-time Voice-based Hate Speech Detection in Social Virtual Realitycited by 0
  22. 2024WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Modelscited by 0
  23. 2026IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimizationcited by 0