mlsanityData to 7 Oct 2026

Language Decision Transformers with Exponential Tilt for Interactive Text Environments

arXiv 2302.05507 ↗First posted 10 Feb 2023cs.CL cs.AI cs.LGcited by 3

On the map: Offline RL and imitation learning from data → Decision transformers and sequence modeling

Abstract (arXiv)

Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards. We address these challenges by proposing Language Decision Transformers (LDTs), a framework that is based on transformer language models and decision transformers (DTs). Our LDTs extend DTs with 3 components: (1) exponential tilt to guide the agent towards high obtainable goals, (2) novel goal conditioning methods yielding better results than the traditional return-to-go (sum of all future rewards), and (3) a model of future observations that improves agent performance. LDTs are the first to address offline RL with DTs on these challenging games. Our experiments show that LDTs achieve the highest scores among many different types of agents on some of the most challenging Jericho games, such as Enchanter.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data. Builds on 25 of its 32 references that are in the map. First posted on arXiv 10 Feb 2023.

Builds on

25 of 32 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Multi-Game Decision Transformers30 May
  2. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problem3 Jun
  3. 2021Decision Transformer: Reinforcement Learning via Sequence Modeling2 Jun

Other references · 22

  1. 2017Graph Attention Networkscited by 8,854
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  6. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
  7. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  8. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  9. 2019Interactive Fiction Games: A Colossal Adventurecited by 165
  10. 2019Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actionscited by 124
  11. 2020Keep CALM and Explore: Language Models for Action Generation in Text-based Gamescited by 108
  12. 2019Reward-Conditioned Policiescited by 101
10 more
  1. 2015Deep Reinforcement Learning with a Natural Language Action Spacecited by 88
  2. 2020Graph Constrained Reinforcement Learning for Natural Language Action Spacescited by 80
  3. 2020How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worldscited by 38
  4. 2020Planning from Pixels using Inverse Dynamics Modelscited by 36
  5. 2020Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learningcited by 27
  6. 2019Learning to Reach Goals via Iterated Supervised Learningcited by 26
  7. 2020Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Gamescited by 22
  8. 2022Multi-Stage Episodic Control for Strategic Exploration in Text Gamescited by 22
  9. 2021Pre-trained Language Models as Prior Knowledge for Playing Text-based Gamescited by 21
  10. 2021Case-based Reasoning for Better Generalization in Textual Reinforcement Learningcited by 8

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2023LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Modelscited by 84
  2. 2024CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learningcited by 26
  3. 2024LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Neededcited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2025TextAtari: 100K Frames Game Playing with Language Agents
  2. 2026GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
  3. 2025Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs
  4. 2024Large Language Models as Agents in Two-Player Games
  5. 2024A Survey on Large Language Model-Based Game Agents
  6. 2024STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making
  7. 2021Learning Knowledge Graph-based World Models of Textual Environments
  8. 2026Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play