Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models

• URL: http://arxiv.org/abs/2305.14718v5
• Date: Sat, 20 Apr 2024 00:34:59 GMT
• Title: Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
• Authors: Ashutosh Baheti, Ximing Lu, Faeze Brahman, Ronan Le Bras, Maarten Sap, Mark Riedl,
• Abstract summary: We introduce Advantage-Leftover Lunch RL (A-LoL), a new class of offline policy gradient algorithms. A-LoL allows incorporating sequence-level classifiers or human-designed scoring functions as rewards. We demonstrate the effectiveness of A-LoL and its variants with a set of four different language generation tasks.
• Score: 39.98853470968973
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning with Human Feedback (RLHF) is the most prominent method for Language Model (LM) alignment. However, RLHF is an unstable and data-hungry process that continually requires new high-quality LM-generated data for finetuning. We introduce Advantage-Leftover Lunch RL (A-LoL), a new class of offline policy gradient algorithms that enable RL training on any pre-existing data. By assuming the entire LM output sequence as a single action, A-LoL allows incorporating sequence-level classifiers or human-designed scoring functions as rewards. Subsequently, by using LM's value estimate, A-LoL only trains on positive advantage (leftover) data points, making it resilient to noise. Overall, A-LoL is an easy-to-implement, sample-efficient, and stable LM training recipe. We demonstrate the effectiveness of A-LoL and its variants with a set of four different language generation tasks. We compare against both online RL (PPO) and recent preference-based (DPO, PRO) and reward-based (GOLD) offline RL baselines. On the commonly-used RLHF benchmark, Helpful and Harmless Assistant (HHA), LMs trained with A-LoL methods achieve the highest diversity while also being rated more safe and helpful than the baselines according to humans. Additionally, in the remaining three tasks, A-LoL could optimize multiple distinct reward functions even when using noisy or suboptimal training data. We also release our experimental code. https://github.com/abaheti95/LoL-RL

Related papers

• Reward Difference Optimization For Sample Reweighting In Offline RLHF [18.62836654699957]
  Current offline RLHF only captures the "ordinal relationship" between responses, overlooking the crucial aspect of how much one is preferred over the others. We propose a simple yet effective solution called Reward Difference Optimization, shorted as RDO. Experiments with 7B LLMs on the HH and TL;DR datasets substantiate the effectiveness of our method in both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2024-08-18T07:04:16Z)
• TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning [7.9961739811640244]
  Development of Large Language Models often confronts challenges stemming from heavy reliance on human annotators. In this work, we pivot to Reinforcement Learning -- but with a twist. We use RL to directly generate the foundational instruction dataset that alone suffices for fine-tuning.
  arXiv  Detail & Related papers  (2024-03-13T16:57:57Z)
• 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)
• Reflect-RL: Two-Player Online RL Fine-Tuning for LMs [38.5495318990769]
  We propose Reflect-RL, a system to fine-tune language models (LMs) using online reinforcement learning (RL) and supervised fine-tuning (SFT) Test results indicate GPT-2 XL 1.56B fine-tuned with Reflect-RL outperforms larger open-source LMs, such as Mistral 7B.
  arXiv  Detail & Related papers  (2024-02-20T01:04:21Z)
• Direct Language Model Alignment from Online AI Feedback [78.40436231613754]
  Direct alignment from preferences (DAP) methods have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF) In this study, we posit that online feedback is key and improves DAP methods. Our method, online AI feedback (OAIF) uses an LLM as annotator: on each training, we sample two responses from the current model and prompt the LLM annotator to choose which one is preferred, thus providing online feedback.
  arXiv  Detail & Related papers  (2024-02-07T12:31:13Z)
• Language Reward Modulation for Pretraining Reinforcement Learning [61.76572261146311]
  We propose leveraging the capabilities of LRFs as a pretraining signal for reinforcement learning. Our VLM pretraining approach, which is a departure from previous attempts to use LRFs, can warmstart sample-efficient learning on robot manipulation tasks.
  arXiv  Detail & Related papers  (2023-08-23T17:37:51Z)
• Reinforced Self-Training (ReST) for Language Modeling [56.75447441157628]
  Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences. We propose a simple algorithm for aligning LLMs with human preferences inspired by growing batch reinforcement learning (RL), which we call Reinforced Self-Training (ReST) Our results show that ReST can substantially improve translation quality, as measured by automated metrics and human evaluation on machine translation benchmarks in a compute and sample-efficient manner.
  arXiv  Detail & Related papers  (2023-08-17T14:12:48Z)
• Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization [73.74371798168642]
  We introduce an open-source modular library, RL4LMs, for optimizing language generators with reinforcement learning. Next, we present the GRUE benchmark, a set of 6 language generation tasks which are supervised not by target strings, but by reward functions. Finally, we introduce an easy-to-use, performant RL algorithm, NLPO, that learns to effectively reduce the action space in language generation.
  arXiv  Detail & Related papers  (2022-10-03T21:38:29Z)

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.