ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Yifei Zhou; Andrea Zanette; Jiayi Pan; Sergey Levine; Aviral Kumar

2024 ICML ICML 2024

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing and Reinforcement Learning

Authors

Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar

Topics

Natural Language Processing > Generation > Dialogue Systems Reinforcement Learning > Methods > Multi-Agent Systems Artificial Intelligence > Core AI > Large Language Models

Keywords

language model agent delayed reward actor-critic framework off-policy rl hierarchical multi-turn rl token-by-token policy

Download PDF