mlsanityData to 14 Oct 2026

LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning

arXiv 2508.05977 ↗First posted 8 Aug 2025cs.LG physics.flu-dyncited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

In the domain of scientific machine learning, designing effective reward functions remains a challenge in reinforcement learning (RL), particularly in environments where task goals are difficult to specify numerically. Reward functions in existing work are predominantly based on heuristics, manual engineering, or task-specific tuning. In this work, we introduce a semantically aligned reinforcement learning method where rewards are computed by aligning the current state with a target semantic instruction using a Sentence-Bidirectional Encoder Representations from Transformers (SBERT). Instead of relying on manually defined reward functions, the policy receives feedback based on the reward, which is a cosine similarity between the goal textual description and the statement description in the episode. We evaluated our approach in several environments and showed that semantic reward can guide learning to achieve competitive control behavior, even in the absence of hand-crafted reward functions. Our study demonstrates a correlation between the language embedding space and the conventional Euclidean space. This framework opens new horizons for aligning agent behavior with natural language goals and lays the groundwork for a more seamless integration of larger language models (LLMs) and fluid control applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 21 of its 31 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

21 of 31 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  7. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
  8. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  9. 2023An LLM Compiler for Parallel Function Callingcited by 179
  10. 2023The Learnability of In-Context Learningcited by 127
  11. 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
  12. 2023LLMLight: Large Language Models as Traffic Signal Control Agentscited by 73
9 more
  1. 2020RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Controlcited by 59
  2. 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policycited by 32
  3. 2024A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learningcited by 30
  4. 2024Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learningcited by 23
  5. 2025Trajectory Prediction Meets Large Language Models: A Surveycited by 14
  6. 2023DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysiscited by 11
  7. 2024Using Large Language Models for Parametric Shape Optimizationcited by 7
  8. 2025Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunitiescited by 7
  9. 2023Online identification and control of PDEs via Reinforcement Learning methodscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning
  2. 2026The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination
  3. 2025Parent-Guided Semantic Reward Model (PGSRM): Embedding-Based Reward Functions for Reinforcement Learning of Transformer Language Models
  4. 2019From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
  5. 2023Reward Design with Language Models
  6. 2018Learning to Understand Goal Specifications by Modelling Reward
  7. 2025Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs
  8. 2025Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games