REBEL: Reinforcement Learning via Regressing Relative Rewards

• URL: http://arxiv.org/abs/2404.16767v3
• Date: Sun, 1 Sep 2024 19:54:56 GMT
• Title: REBEL: Reinforcement Learning via Regressing Relative Rewards
• Authors: Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kianté Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun,
• Abstract summary: We propose REBEL, a minimalist RL algorithm for the era of generative models. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL. We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
• Score: 59.68420022466047
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g. value networks, clipping), and is notorious for its sensitivity to the precise implementation of these components. In response, we take a step back and ask what a minimalist RL algorithm for the era of generative models would look like. We propose REBEL, an algorithm that cleanly reduces the problem of policy optimization to regressing the relative reward between two completions to a prompt in terms of the policy, enabling strikingly lightweight implementation. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL, which allows us to match the strongest known theoretical guarantees in terms of convergence and sample complexity in the RL literature. REBEL can also cleanly incorporate offline data and be extended to handle the intransitive preferences we frequently see in practice. Empirically, we find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO, all while being simpler to implement and more computationally efficient than PPO. When fine-tuning Llama-3-8B-Instruct, REBEL achieves strong performance in AlpacaEval 2.0, MT-Bench, and Open LLM Leaderboard.

Related papers

• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback [38.61232011566285]
  We study the recently proposed model of RL with Aggregate Bandit Feedback (RL-ABF), where the agent only observes the sum of rewards at the end of an episode instead of each reward individually. In this paper, we extend ABF to linear function approximation and develop two efficient algorithms with near-optimal regret guarantees.
  arXiv  Detail & Related papers  (2024-05-13T10:51:01Z)
• 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)
• Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment [37.52249093928251]
  This paper proposes a new framework, reinforcement learning with relative feedback, and a novel trajectory-wise policy gradient algorithm. We show theoretically that P3O is invariant to equivalent rewards and avoids the complexity of PPO. Empirical evaluations demonstrate that P3O outperforms PPO in the KL-Reward trade-off and can align with human preferences as well as or better than prior methods.
  arXiv  Detail & Related papers  (2023-09-30T01:23:22Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)
• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning [132.45959478064736]
  We propose a general framework that unifies model-based and model-free reinforcement learning. We propose a novel estimation function with decomposable structural properties for optimization-based exploration. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed.
  arXiv  Detail & Related papers  (2022-09-30T17:59:16Z)
• LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning [78.2286146954051]
  LCRL implements model-free Reinforcement Learning (RL) algorithms over unknown Decision Processes (MDPs) We present case studies to demonstrate the applicability, ease of use, scalability, and performance of LCRL.
  arXiv  Detail & Related papers  (2022-09-21T13:21:00Z)
• Pessimistic Model-based Offline RL: PAC Bounds and Posterior Sampling under Partial Coverage [33.766012922307084]
  We study model-based offline Reinforcement Learning with general function approximation. We present an algorithm named Constrained Policy Optimization (CPPO) which leverages a general function class and uses a constraint to encode pessimism.
  arXiv  Detail & Related papers  (2021-07-13T16:30:01Z)
• Structured Policy Iteration for Linear Quadratic Regulator [40.52288246664592]
  We introduce the textitStructured Policy Iteration (S-PI) for LQR, a method capable of deriving a structured linear policy. Such a structured policy with (block) sparsity or low-rank can have significant advantages over the standard LQR policy. In both the known-model and model-free setting, we prove convergence analysis under the proper choice of parameters.
  arXiv  Detail & Related papers  (2020-07-13T06:03:15Z)

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.