mlsanityData to 14 Oct 2026

Integrating LLMs and Decision Transformers for Language Grounded Generative Quality-Diversity

arXiv 2308.13278 ↗First posted 25 Aug 2023cs.LG cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Quality-Diversity is a branch of stochastic optimization that is often applied to problems from the Reinforcement Learning and control domains in order to construct repertoires of well-performing policies/skills that exhibit diversity with respect to a behavior space. Such archives are usually composed of a finite number of reactive agents which are each associated to a unique behavior descriptor, and instantiating behavior descriptors outside of that coarsely discretized space is not straight-forward. While a few recent works suggest solutions to that issue, the trajectory that is generated is not easily customizable beyond the specification of a target behavior descriptor. We propose to jointly solve those problems in environments where semantic information about static scene elements is available by leveraging a Large Language Model to augment the repertoire with natural language descriptions of trajectories, and training a policy conditioned on those descriptions. Thus, our method allows a user to not only specify an arbitrary target behavior descriptor, but also provide the model with a high-level textual prompt to shape the generated trajectory. We also propose an LLM-based approach to evaluating the performance of such generative agents. Furthermore, we develop a benchmark based on simulated robot navigation in a 2d maze that we use for experimental validation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 25 Aug 2023.

Builds on

33 of 47 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  11. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  12. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
21 more
  1. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  3. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 516
  4. 2015Illuminating search spaces by mapping elitescited by 425
  5. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  6. 2019Learning Latent Plans from Playcited by 316
  7. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  8. 2023ConceptFusion: Open-set Multimodal 3D Mappingcited by 304
  9. 2023Imitating Human Behaviour with Diffusion Modelscited by 263
  10. 2023Reward Design with Language Modelscited by 261
  11. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 212
  12. 2014Robots that can adapt like animalscited by 204
  13. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 164
  14. 2020Language-Conditioned Imitation Learning for Robot Manipulation Taskscited by 136
  15. 2019Behaviour Suite for Reinforcement Learningcited by 132
  16. 2022DALL-E-Bot: Introducing Web-Scale Diffusion Models to Roboticscited by 106
  17. 2020Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimizationcited by 54
  18. 2019From exploration to control: learning object manipulation skills through novelty search and local adaptationcited by 13
  19. 2023The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformerscited by 10
  20. 2022Towards QD-suite: developing a set of benchmarks for Quality-Diversity algorithmscited by 1
  21. 2022E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectoriescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating the Diversity and Quality of LLM Generated Content
  2. 2025Jointly Reinforcing Diversity and Quality in Language Model Generations
  3. 2026Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning
  4. 2025Post-training Large Language Models for Diverse High-Quality Responses
  5. 2025Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models
  6. 2026Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
  7. 2026Behavioral Foundation Models for Quality Diversity
  8. 2026SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning