Keep CALM and Explore: Language Models for Action Generation in Text-based Games
Text-based games present a unique challenge for autonomous agents to operate in natural language and handle enormous action spaces. In this paper, we propose the Contextual Action Language Model (CALM) to generate a compact set of action candidates at each game state. Our key insight is to train language models on human gameplay, where people demonstrate linguistic priors and a general game sense for promising actions conditioned on game history. We combine CALM with a reinforcement learning agent which re-ranks the generated action candidates to maximize in-game rewards. We evaluate our approach using the Jericho benchmark, on games unseen by CALM during training. Our method obtains a 69% relative improvement in average game score over the previous state-of-the-art model. Surprisingly, on half of these games, CALM is competitive with or better than other models that have access to ground truth admissible actions. Code and data are available at https://github.com/princeton-nlp/calm-textgame.
Code (1)
Tasks
Action GenerationLanguage ModelingLanguage Modellingtext-based gamesSimilar Papers 제목 키워드 기반
Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games
Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. CALM, a popular approach, leverages linguistic priors of LLMs -- GPT-2 -- for action candidate recommendations to …
Language ModelingLanguage Modellingtext-based gamesKeep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers
Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignment and Concept Manipulation CALM, an inf…
Function-Guided Conditional Generation Using Protein Language Models with Adapters
The conditional generation of proteins with desired functions is a key goal for generative models. Existing methods based on prompting of protein language models (PLMs) can generate proteins conditioned on a target funct…
Language ModelingLanguage ModellingCALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture…
General KnowledgeLanguage ModelingLanguage ModellingMedQA+1Equanimity in HRI: Applying Calm Technology Principles to Human-Robot Interaction
This paper explores how {\textit{Calm Technology}} can be integrated into Human-Robot Interaction (HRI), with a particular focus on the household environment. It offers comprehensive guidelines for designing assistive ro…