Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts

arXiv:2404.09248v1 Announce Type: new
Abstract: Reinforcement learning (RL) trains agents to accomplish complex tasks through environmental interaction data, but its capacity is also limited by the scope of the available data. To obtain a knowledgeable agent, a promising approach is to leverage the knowledge from large language models (LLMs). Despite previous studies combining LLMs with RL, seamless integration of the two components remains challenging due to their semantic gap. This paper introduces a novel method, Knowledgeable Agents from Language Model …

abstract agent agents arxiv capacity cs.ai cs.cl cs.lg data environmental knowledge language language model language models large language large language model large language models llms offline reinforcement reinforcement learning tasks through trains type