Natural Language Generation Using Reinforcement Learning with External Rewards

2019-11-26 · Vidhushini Srinivasan, Sashank Santhanam, Samira Shaikh

We propose an approach towards natural language generation using a bidirectional encoder-decoder which incorporates external rewards through reinforcement learning (RL). We use attention mechanism and maximum mutual information as an initial objective function using RL. Using a two-part training scheme, we train an external reward analyzer to predict the external rewards and then use the predicted rewards to maximize the expected rewards (both internal and external). We evaluate the system on two standard dialogue corpora - Cornell Movie Dialog Corpus and Yelp Restaurant Review Corpus. We report standard evaluation metrics including BLEU, ROUGE-L, and perplexity as well as human evaluation to validate our approach.

📄 PDF Abstract BibTeX arXiv:1911.11404

Code (1)

VidhushiniSrinivasan16/ICMLA 공식 구현 tf

Tasks

Decoder reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Text Generation

Learning to Reason without External Rewards

2025-05-26 · Xuandong Zhao, Zhewei Kang, Aosong Feng, Sergey Levine 외

Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement …

Code Generation reinforcement-learning Reinforcement Learning

IRIS: Intrinsic Reward Image Synthesis

2025-09-29 · Yihang Chen, Yuanhao Ban, Yunqi Hong, Cho-Jui Hsieh arxiv

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in language reasoning, its application to autoregressive Text-to-Image (T2I) generation is often constrained by the limited availability of human p…

Reinforcement Learning Image Generation

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

2026-03-04 · Lei Huang, Xiang Cheng, Chenxiao Zhao, Guobin Shen 외 arxiv

Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorithms rely solely on scalar rewards, leavi…

Reinforcement Learning

Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards

2026-03-01 · Seungwook Kim, Minsu Cho arxiv

Text-to-image generation powers content creation across design, media, and data augmentation. Post-training of text-to-image generative models is a promising path to improve human preference alignment, factuality, and ae…

Text-to-Image Generation Reinforcement Learning Data Augmentation

Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation

2026-01-07 · Longwen Wang, Yirui Liu, Xuan'er Wu, Xiaohui Hu 외 arxiv

Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but induce sparsity, while external Reward Mod…

Reinforcement Learning Code Generation