Challenge: Text-based games present a unique challenge for autonomous agents to operate in natural language and handle enormous action spaces.
Approach: They propose a Contextual Action Language Model (CALM) to generate a compact set of action candidates at each game state.
Outcome: The proposed model achieves a 69% improvement in average game score on unsupervised games . the proposed model is competitive with or better than other models that have access to ground truth admissible actions on half of the games tested .

Similar Papers

Self-imitation Learning for Action Generation in Text-based Games (2023.eacl-main)

Copied to clipboard

Challenge: Text-based games are situated systems where the game agents observe textual descriptions, and generate textual commands to interact with the environment.
Approach: They propose a confidence-based self-imitation model to generate action candidates for the RL agent by exploiting past valuable trajectories to adapt a pre-trained language model towards a target game.
Outcome: The proposed model performs well in multiple challenging games.
LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues.
Approach: They propose a linguistically-grounded game-theoretic paradigm for multi-agent dialogue generation that uses a training-free equilibrium approximation algorithm to model dialogue over communicative intents and strategies.
Outcome: The proposed framework improves agents’ communication efficiency by helping them convey their intended meaning more effectively through language.
Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games (2022.acl-short)

Copied to clipboard

Challenge: Existing RL agents are far away from solving text-based games due to their combinatorially large action spaces that hinders efficient exploration.
Approach: They propose an exploration technique that injects external commonsense knowledge, via a pretrained language model, into the agent during training when the agent is the most uncertain about its next action.
Outcome: The proposed method exhibits improvement on the collected game scores during the training in four out of nine games from Jericho.
Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games (2022.findings-emnlp)

Copied to clipboard

Challenge: Language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning has become the dominant paradigm in NLP.
Approach: They propose to train language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning on the target domain.
Outcome: The proposed model improves on the previous state-of-the-art model on the Jericho Walkthroughs dataset by 49%.
On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning (2025.coling-main)

Copied to clipboard

Challenge: Text-based reinforcement learning is a form of interactive fiction where players manipulate the environment using text and admissible actions in natural language.
Approach: They show that rich semantic understanding leads to efficient training of text-based RL agents . they also show that semantic degeneration occurs when LMs are inappropriately fine-tuned .
Outcome: The results suggest that semantic understanding is not important for the task . they also show that fine-tuning language models can degenerate the agent's performance .
From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)

Copied to clipboard

Challenge: Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time.
Approach: They propose a framework that reframes language modeling as next-state prediction under interaction.
Outcome: The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics .
Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based Games (2023.findings-acl)

Copied to clipboard

Challenge: Existing reinforcement learning frameworks fail to decompose the task and abstract the action autonomously.
Approach: They propose a skill-centric reinforcement learning framework capable of abstracting the action in an end-to-end manner.
Outcome: Empirical experiments on the Jericho environment validate the proposed framework against state-of-the-art baselines.
Reader: Model-based language-instructed reinforcement learning (2023.emnlp-main)

Copied to clipboard

Challenge: Existing models of RL are limited and need to be re-trained for every new problem.
Approach: They propose a model-based reinforcement learning approach to tackle the environment Read To Fight Monsters, a grounded policy learning problem.
Outcome: The proposed approach performs better than existing model-free SOTA agents in the read to fight monsters environment and is more sample efficient than existing models.
A Survey of Text Games for Reinforcement Learning Informed by Natural Language (2022.tacl-1)

Copied to clipboard

Challenge: Interactive Fiction Games (text games) are a problem type that require natural language to solve complex tasks.
Approach: They propose to use interactive fiction games as a testing environment to test the new Reinforcement Learning solutions using natural language.
Outcome: The proposed solutions are based on the proposed interactive fiction games and the generated environments.
Language Models are Few-Shot Butlers (2021.emnlp-main)

Copied to clipboard

Challenge: Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets.
Approach: They propose a two-stage procedure to learn from a small set of demonstrations and a simple reinforcement learning algorithm to improve by interacting with an environment.
Outcome: The proposed method improves with only 1.2% of the demonstrations and a simple reinforcement learning algorithm over existing methods in the ALFWorld environment.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations