ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation

• URL: http://arxiv.org/abs/2308.02223v1
• Date: Fri, 4 Aug 2023 09:35:45 GMT
• Title: ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
• Authors: Chenglong Wang, Hang Zhou, Yimin Hu, Yifu Huo, Bei Li, Tongran Liu, Tong Xiao, Jingbo Zhu
• Abstract summary: We introduce two-stage sampling and dynamic sampling approaches to improve the sampling efficiency during training sequence generation models via RL. Experimental results show that the efficient sampling-based RL, referred to as ESRL, can outperform all baselines in terms of both training efficiency and memory consumption.
• Score: 43.506732624371786
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences. This is a computational challenge as presented by the practice of sequence generation problems, such as machine translation, where we often deal with a large action space (\textit{e.g.,} a vocabulary) and a long action sequence (\textit{e.g.,} a translation). In this work, we introduce two-stage sampling and dynamic sampling approaches to improve the sampling efficiency during training sequence generation models via RL. We experiment with our approaches on the traditional sequence generation tasks, including machine translation and abstractive summarization. Furthermore, we evaluate our approaches in RL from human feedback (RLHF) through training a large language model using the reward model. Experimental results show that the efficient sampling-based RL, referred to as ESRL, can outperform all baselines in terms of both training efficiency and memory consumption. Notably, ESRL yields consistent performance gains over the strong REINFORCE, minimum risk training, and proximal policy optimization methods.

Related papers

• Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models [11.624678008637623]
  We propose separating generation and learning in RLHF. Asynchronous training relies on an underexplored regime, online but off-policy RLHF. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost.
  arXiv  Detail & Related papers  (2024-10-23T19:59:50Z)
• Teaching Large Language Models to Reason with Reinforcement Learning [38.17625148525193]
  Reinforcement Learning from Human Feedback (textbfRLHF) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback.
  arXiv  Detail & Related papers  (2024-03-07T16:36:29Z)
• 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)
• KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning [25.421649004269373]
  In task-oriented dialogs (TOD), reinforcement learning algorithms train a model to directly optimize response for task-related metrics. We investigate an approach to create a more efficient RL-based algorithm to improve TOD performance in an offline setting. Experiments on the MultiWoZ dataset show our new training algorithm, Keywords Reinforcement Learning with Next-word Sampling (KRLS), achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-11-30T06:27:46Z)
• Teacher Forcing Recovers Reward Functions for Text Generation [21.186397113834506]
  We propose a task-agnostic approach that derives a step-wise reward function directly from a model trained with teacher forcing. We additionally propose a simple modification to stabilize the RL training on non-parallel datasets with our induced reward function.
  arXiv  Detail & Related papers  (2022-10-17T02:48:58Z)
• Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective [142.36200080384145]
  We propose a single objective which jointly optimize a latent-space model and policy to achieve high returns while remaining self-consistent. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods.
  arXiv  Detail & Related papers  (2022-09-18T03:51:58Z)
• Improving Non-autoregressive Generation with Mixup Training [51.61038444990301]
  We present a non-autoregressive generation model based on pre-trained transformer models. We propose a simple and effective iterative training method called MIx Source and pseudo Target. Our experiments on three generation benchmarks including question generation, summarization and paraphrase generation, show that the proposed framework achieves the new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-10-21T13:04:21Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)

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.