Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM

• URL: http://arxiv.org/abs/2505.10861v1
• Date: Fri, 16 May 2025 05:03:39 GMT
• Title: Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM
• Authors: Thang Duong, Minglai Yang, Chicheng Zhang,
• Abstract summary: We investigate the usage of Large Language Model (LLM) in collecting high-quality data to warm-start Reinforcement Learning (RL) algorithms.<n>Our algorithm, LORO, can both converge to an optimal policy and have a high sample efficiency.<n>On multiple OpenAI Gym environments, such as CartPole and Pendulum, we empirically demonstrate that LORO outperforms baseline algorithms.
• Score: 14.139788456751706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate the usage of Large Language Model (LLM) in collecting high-quality data to warm-start Reinforcement Learning (RL) algorithms for learning in some classical Markov Decision Process (MDP) environments. In this work, we focus on using LLM to generate an off-policy dataset that sufficiently covers state-actions visited by optimal policies, then later using an RL algorithm to explore the environment and improve the policy suggested by the LLM. Our algorithm, LORO, can both converge to an optimal policy and have a high sample efficiency thanks to the LLM's good starting policy. On multiple OpenAI Gym environments, such as CartPole and Pendulum, we empirically demonstrate that LORO outperforms baseline algorithms such as pure LLM-based policies, pure RL, and a naive combination of the two, achieving up to $4 \times$ the cumulative rewards of the pure RL baseline.

Related papers

• DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation [83.21140655248624]
  Large language models (LLMs) have been introduced into recommender systems (RSs)<n>We propose DeepRec, a novel LLM-based RS that enables autonomous multi-turn interactions between LLMs and TRMs for deep exploration of the item space.<n> Experiments on public datasets demonstrate that DeepRec significantly outperforms both traditional and LLM-based baselines.
  arXiv  Detail & Related papers  (2025-05-22T15:49:38Z)
• ShiQ: Bringing back Bellman to LLMs [37.70964838115103]
  We build a practical algorithm, ShiQ for Shifted-Q, that supports off-policy, token-wise learning while remaining simple to implement.<n>We evaluate ShiQ on both synthetic data and real-world benchmarks, e.g., UltraFeedback and BFCL-V3, demonstrating its effectiveness in both single-turn and multi-turn LLM settings.
  arXiv  Detail & Related papers  (2025-05-16T10:12:11Z)
• A Comprehensive Analysis on LLM-based Node Classification Algorithms [21.120619437937382]
  We develop a comprehensive and testbed for node classification using Large Language Models (LLMs)<n>It includes ten datasets, eight LLM-based algorithms, and three learning paradigms, and is designed for easy extension with new methods and datasets.<n>We conduct extensive experiments, training and evaluating over 2,200 models, to determine the key settings that affect performance.<n>Our findings uncover eight insights, e.g., LLM-based methods can significantly outperform traditional methods in a semi-supervised setting, while the advantage is marginal in a supervised setting.
  arXiv  Detail & Related papers  (2025-02-02T15:56:05Z)
• EVOLvE: Evaluating and Optimizing LLMs For Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications. Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Value Augmented Sampling for Language Model Alignment and Personalization [39.070662999014836]
  We present a new framework for reward optimization, Value Augmented Sampling (VAS) VAS solves for the optimal reward-maximizing policy without co-training the policy and the value function. Our algorithm unlocks the new capability of composing several rewards and controlling the extent of each one during deployment time.
  arXiv  Detail & Related papers  (2024-05-10T17:59:04Z)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization [17.729842629392742]
  We study a Reinforcement Learning problem in which we are given a set of trajectories collected with K baseline policies. The goal is to learn a policy which performs as well as the best combination of baselines on the entire state space.
  arXiv  Detail & Related papers  (2024-03-28T14:34:02Z)
• Fine-Tuning Language Models with Reward Learning on Policy [68.70065254564642]
  Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. Despite its popularity, (fixed) reward models may suffer from inaccurate off-distribution. We propose reward learning on policy (RLP), an unsupervised framework that refines a reward model using policy samples to keep it on-distribution.
  arXiv  Detail & Related papers  (2024-03-28T10:02:10Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning [37.10401435242991]
  Large language models (LLMs) often fail in solving simple decision-making tasks due to misalignment of the knowledge in LLMs with environments. We propose TWOSOME, a novel framework that deploys LLMs as decision-making agents to efficiently interact and align with embodied environments via RL.
  arXiv  Detail & Related papers  (2024-01-25T13:03:20Z)
• Learning to Generate Better Than Your LLM [16.74454360961681]
  Reinforcement learning has emerged as a powerful paradigm for fine-tuning Large Language Models. We extend RL algorithms to allow them to interact with a dynamic black-box guide LLM. We show that our RL algorithms achieve higher performance than supervised learning.
  arXiv  Detail & Related papers  (2023-06-20T18:19:17Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)

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.