A Theoretical Framework for Partially Observed Reward-States in RLHF

• URL: http://arxiv.org/abs/2402.03282v3
• Date: Sat, 09 Nov 2024 07:09:00 GMT
• Title: A Theoretical Framework for Partially Observed Reward-States in RLHF
• Authors: Chinmaya Kausik, Mirco Mutti, Aldo Pacchiano, Ambuj Tewari,
• Abstract summary: We model reinforcement learning with partially observed reward-states (PORRL) We accommodate two kinds of feedback $-$ cardinal and dueling feedback. In both feedback settings, we show that our models and guarantees generalize and extend existing ones.
• Score: 39.41038579993645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The growing deployment of reinforcement learning from human feedback (RLHF) calls for a deeper theoretical investigation of its underlying models. The prevalent models of RLHF do not account for neuroscience-backed, partially-observed "internal states" that can affect human feedback, nor do they accommodate intermediate feedback during an interaction. Both of these can be instrumental in speeding up learning and improving alignment. To address these limitations, we model RLHF as reinforcement learning with partially observed reward-states (PORRL). We accommodate two kinds of feedback $-$ cardinal and dueling feedback. We first demonstrate that PORRL subsumes a wide class of RL problems, including traditional RL, RLHF, and reward machines. For cardinal feedback, we present two model-based methods (POR-UCRL, POR-UCBVI). We give both cardinal regret and sample complexity guarantees for the methods, showing that they improve over naive history-summarization. We then discuss the benefits of a model-free method like GOLF with naive history-summarization in settings with recursive internal states and dense intermediate feedback. For this purpose, we define a new history aware version of the Bellman-eluder dimension and give a new guarantee for GOLF in our setting, which can be exponentially sharper in illustrative examples. For dueling feedback, we show that a naive reduction to cardinal feedback fails to achieve sublinear dueling regret. We then present the first explicit reduction that converts guarantees for cardinal regret to dueling regret. In both feedback settings, we show that our models and guarantees generalize and extend existing ones.

Related papers

• Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping [0.0]
  Reinforcement learning often faces challenges with reward misalignment. Human-in-the-loop (HIL) methods may exacerbate the problem, as humans are prone to biases that lead to inconsistent, subjective, or misaligned feedback.
  arXiv  Detail & Related papers  (2025-03-26T03:17:12Z)
• Reward Shaping to Mitigate Reward Hacking in RLHF [47.71454266800376]
  Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models with human values. reward shaping helps stabilize RLHF and partially mitigate reward hacking. We present a comprehensive study of the prevalent reward shaping methods. We propose Preference As Reward (PAR), a novel approach that leverages the latent preferences embedded within the reward model itself as the signal for reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-26T02:57:59Z)
• Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits [59.30310692855397]
  We propose a unified framework for the RLHF pipeline from the view of contextual bandits. We decompose the RLHF process into two distinct stages: (post-)training and deployment. We then develop novel algorithms for each stage, demonstrating significant improvements in both statistical and computational efficiency.
  arXiv  Detail & Related papers  (2025-02-11T02:36:01Z)
• Reinforcement Learning with Segment Feedback [56.54271464134885]
  We consider a model named RL with segment feedback, which offers a general paradigm filling the gap between per-state-action feedback and trajectory feedback. Under binary feedback, increasing the number of segments $m$ decreases the regret at an exponential rate; in contrast, surprisingly, under sum feedback, increasing $m$ does not reduce the regret significantly.
  arXiv  Detail & Related papers  (2025-02-03T23:08:42Z)
• Reward Modeling with Ordinal Feedback: Wisdom of the Crowd [9.034189257088762]
  Learning a reward model (RM) from human preferences has been an important component in aligning large language models. We propose a framework for learning RMs under ordinal feedback. We prove the statistical benefits of ordinal feedback in terms of reducing the Rademacher complexity.
  arXiv  Detail & Related papers  (2024-11-19T20:17:04Z)
• Optimal Design for Reward Modeling in RLHF [83.3614658277817]
  We formalize the reward training model in Reinforcement Learning from Human Feedback. We frame the selection of an effective dataset as a simple regret minimization task. We derive bounds on the simple regret under appropriate assumptions.
  arXiv  Detail & Related papers  (2024-10-22T14:36:44Z)
• Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback [8.601283886845664]
  Reinforcement learning from human feedback (RLHF) aligns Large language models (LLMs) with human intentions and values. Despite its effectiveness and popularity, RLHF is prone to biased local optimization. We propose a novel textitsequence-to-sequence (seq2seq) reward modeling method.
  arXiv  Detail & Related papers  (2024-08-30T16:14:35Z)
• The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization [8.911768677958753]
  This work is the first to openly reproduce the Reinforcement Learning from Human Feedback scaling behaviors reported in OpenAI's seminal TL;DR summarization work. We create an RLHF pipeline from scratch, enumerate over 20 key implementation details, and share key insights during the reproduction.
  arXiv  Detail & Related papers  (2024-03-24T02:59:27Z)
• Unfamiliar Finetuning Examples Control How Language Models Hallucinate [75.03210107477157]
  Large language models are known to hallucinate when faced with unfamiliar queries. We find that unfamiliar examples in the models' finetuning data are crucial in shaping these errors. Our work further investigates RL finetuning strategies for improving the factuality of long-form model generations.
  arXiv  Detail & Related papers  (2024-03-08T18:28:13Z)
• Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF [79.98542868281471]
  Reinforcement Learning from Human Feedback (RLHF) is a technique that aligns language models closely with human-centric values. It is observed that the performance of the reward model degrades after one epoch of training, and optimizing too much against the learned reward model eventually hinders the true objective. This paper delves into these issues, leveraging the theoretical insights to design improved reward learning algorithm termed 'Iterative Data Smoothing' (IDS)
  arXiv  Detail & Related papers  (2024-01-29T17:43:42Z)
• Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
  We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset. We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
  arXiv  Detail & Related papers  (2024-01-11T17:56:59Z)
• The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback [5.037876196534672]
  Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. In this paper, we illustrate the causes of this issue, reviewing relevant literature from model-based reinforcement learning, and argue for solutions.
  arXiv  Detail & Related papers  (2023-10-31T21:52:41Z)
• SuperHF: Supervised Iterative Learning from Human Feedback [20.22920163075946]
  We focus on two prevalent methods used to align large language models, Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) We propose a novel approach, Supervised Iterative Learning from Human Feedback (SuperHF), which seeks to leverage the strengths of both methods. Our experimental results show SuperHF exceeds PPO-based RLHF on the training objective, easily and favorably trades off high reward with low reward hacking, improves downstream calibration, and performs the same on our GPT-4 based qualitative evaluation scheme all the while being significantly simpler to implement.
  arXiv  Detail & Related papers  (2023-10-25T16:52:00Z)
• A Long Way to Go: Investigating Length Correlations in RLHF [59.49656695716066]
  This paper demonstrates, on three diverse settings, that optimizing for response length is a significant factor behind RLHF. We find improvements in reward to largely be driven by increasing response length, instead of other features. Even a purely length-based reward reproduces most downstream RLHF improvements over supervised fine-tuned models.
  arXiv  Detail & Related papers  (2023-10-05T17:38:28Z)

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.