From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

• URL: http://arxiv.org/abs/2411.03817v2
• Date: Fri, 22 Nov 2024 10:24:44 GMT
• Title: From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
• Authors: Zhirui Deng, Zhicheng Dou, Yutao Zhu, Ji-Rong Wen, Ruibin Xiong, Mang Wang, Weipeng Chen,
• Abstract summary: We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
• Score: 62.54484062185869
• License:
• Abstract: The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems. While traditional methods depend on the inherent knowledge of LLMs without fine-tuning, more recent approaches have shifted toward the reinforcement learning strategy to further enhance agents' ability to solve complex interactive tasks with environments and tools. However, previous approaches are constrained by the sparse reward issue, where existing datasets solely provide a final scalar reward for each multi-step reasoning chain, potentially leading to ineffectiveness and inefficiency in policy learning. In this paper, we introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process. Inheriting the spirit of novice-to-expert theory, we first compare the actions of the expert and the agent to automatically generate intermediate rewards for fine-grained optimization. Additionally, we propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment. Further theoretical analysis demonstrates that the action distribution of the agent can converge toward the expert action distribution over multiple training cycles. Experimental results across various datasets indicate that StepAgent outperforms existing baseline methods.

Related papers

• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
  Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
  arXiv  Detail & Related papers  (2024-06-17T03:29:13Z)
• Multi-Agent Transfer Learning via Temporal Contrastive Learning [8.487274986507922]
  This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals.
  arXiv  Detail & Related papers  (2024-06-03T14:42:14Z)
• Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents [49.85633804913796]
  We present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to enhance the performance of open LLM agents. Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin.
  arXiv  Detail & Related papers  (2024-03-04T21:50:29Z)
• Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization [53.510942601223626]
  Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. These task solvers necessitate manually crafted prompts to inform task rules and regulate behaviors. We propose Agent-Pro: an LLM-based Agent with Policy-level Reflection and Optimization.
  arXiv  Detail & Related papers  (2024-02-27T15:09:20Z)
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents [76.95062553043607]
  evaluating large language models (LLMs) is essential for understanding their capabilities and facilitating their integration into practical applications. We introduce AgentBoard, a pioneering comprehensive benchmark and accompanied open-source evaluation framework tailored to analytical evaluation of LLM agents.
  arXiv  Detail & Related papers  (2024-01-24T01:51:00Z)
• Efficient Reinforcement Learning via Decoupling Exploration and Utilization [6.305976803910899]
  Reinforcement Learning (RL) has achieved remarkable success across multiple fields and applications, including gaming, robotics, and autonomous vehicles. In this work, our aim is to train agent with efficient learning by decoupling exploration and utilization, so that agent can escaping the conundrum of suboptimal Solutions. The above idea is implemented in the proposed OPARL (Optimistic and Pessimistic Actor Reinforcement Learning) algorithm.
  arXiv  Detail & Related papers  (2023-12-26T09:03:23Z)
• MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning [62.065503126104126]
  We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the principal may not know the learning behavior nor the rewards of real people. We introduce MERMAIDE, a model-based meta-learning framework to train a principal that can quickly adapt to out-of-distribution agents.
  arXiv  Detail & Related papers  (2023-04-10T15:44:50Z)
• Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis [14.656957226255628]
  We introduce a model-agnostic method for discovery of behavior clusters in multiagent domains. Our framework makes no assumption about agents' underlying learning algorithms, does not require access to their latent states or models, and can be trained using entirely offline observational data.
  arXiv  Detail & Related papers  (2022-06-17T23:07:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.