paper-with-me

Papers

Offline Reinforcement Learning for Large Scale Language Action Spaces

2021-09-29 · ICLR 2022 4 · Youngsoo Jang, Jongmin Lee, Kee-Eung Kim

Training a task-oriented dialogue agent can be naturally formulated as offline reinforcement learning (RL) problem, where the agent aims to learn a conversational strategy to achieve user goals, only from a dialogue corpus. It is very challenging in terms of RL since the natural language action space is infinitely large, while feasible (syntactically and semantically correct) actions are very sparse. Thus, standard RL methods easily fail and generate responses diverging from human language, even when fine-tuning a powerful pre-trained language model. In this paper, we introduce GPT-Critic, an offline RL method for task-oriented dialogue. GPT-Critic is built upon GPT-2, fine-tuning the language model through behavior cloning of the critic-guided self-generated sentences. GPT-Critic is essentially free from the issue of diverging from human language since it learns from the sentences sampled from the pre-trained language model. In the experiments, we demonstrate that our algorithm outperforms the state-of-the-art in task-oriented dialogue benchmarks including MultiWOZ and ConvLab.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingOffline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Contextual Transformer for Offline Meta Reinforcement Learning

2022-11-15 · Runji Lin, Ye Li, Xidong Feng, Zhaowei Zhang 외

The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in …

D4RLMeta Reinforcement LearningMuJoCoOffline RL+5

Offline Reinforcement Learning With Combinatorial Action Spaces

2024-10-28 · Matthew Landers, Taylor W. Killian, Hugo Barnes, Thomas Hartvigsen 외

Reinforcement learning problems often involve large action spaces arising from the simultaneous execution of multiple sub-actions, resulting in combinatorial action spaces. Learning in combinatorial action spaces is diff…

reinforcement-learningReinforcement Learning

A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

2019-12-01 · NeurIPS 2019 12 · Xueying Bai, Jian Guan, Hongning Wang

Reinforcement learning is effective in optimizing policies for recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with a real environment, and thus are expen…

Generative Adversarial NetworkModel-based Reinforcement LearningRecommendation Systemsreinforcement-learning+2

Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

2019-11-10 · NeurIPS 2019 12 · Xueying Bai, Jian Guan, Hongning Wang

Reinforcement learning is well suited for optimizing policies of recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with the real environment, and thus are e…

Generative Adversarial NetworkModel-based Reinforcement LearningRecommendation Systemsreinforcement-learning+2

QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning

2024-08-20 · Yilun Kong, Hangyu Mao, Qi Zhao, Bin Zhang 외

Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level pe…

BenchmarkingLanguage ModellingMathPrompt Engineering