Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Heng, Alchaer, Haddy, Ajoudani, Arash, She, Yu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915849989783552
author Zhang, Heng
Alchaer, Haddy
Ajoudani, Arash
She, Yu
author_facet Zhang, Heng
Alchaer, Haddy
Ajoudani, Arash
She, Yu
contents We introduce Reward-Zero, a general-purpose implicit reward mechanism that transforms natural-language task descriptions into dense, semantically grounded progress signals for reinforcement learning (RL). Reward-Zero serves as a simple yet sophisticated universal reward function that leverages language embeddings for efficient RL training. By comparing the embedding of a task specification with embeddings derived from an agent's interaction experience, Reward-Zero produces a continuous, semantically aligned sense-of-completion signal. This reward supplements sparse or delayed environmental feedback without requiring task-specific engineering. When integrated into standard RL frameworks, it accelerates exploration, stabilizes training, and enhances generalization across diverse tasks. Empirically, agents trained with Reward-Zero converge faster and achieve higher final success rates than conventional methods such as PPO with common reward-shaping baselines, successfully solving tasks that hand-designed rewards could not in some complex tasks. In addition, we develop a mini benchmark for the evaluation of completion sense during task execution via language embeddings. These results highlight the promise of language-driven implicit reward functions as a practical path toward more sample-efficient, generalizable, and scalable RL for embodied agents. Code will be released after peer review.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09331
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning
Zhang, Heng
Alchaer, Haddy
Ajoudani, Arash
She, Yu
Machine Learning
We introduce Reward-Zero, a general-purpose implicit reward mechanism that transforms natural-language task descriptions into dense, semantically grounded progress signals for reinforcement learning (RL). Reward-Zero serves as a simple yet sophisticated universal reward function that leverages language embeddings for efficient RL training. By comparing the embedding of a task specification with embeddings derived from an agent's interaction experience, Reward-Zero produces a continuous, semantically aligned sense-of-completion signal. This reward supplements sparse or delayed environmental feedback without requiring task-specific engineering. When integrated into standard RL frameworks, it accelerates exploration, stabilizes training, and enhances generalization across diverse tasks. Empirically, agents trained with Reward-Zero converge faster and achieve higher final success rates than conventional methods such as PPO with common reward-shaping baselines, successfully solving tasks that hand-designed rewards could not in some complex tasks. In addition, we develop a mini benchmark for the evaluation of completion sense during task execution via language embeddings. These results highlight the promise of language-driven implicit reward functions as a practical path toward more sample-efficient, generalizable, and scalable RL for embodied agents. Code will be released after peer review.
title Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2603.09331