paper-with-me

Papers

Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations

2018-09-05 · EMNLP 2018 10 · Dipendra Misra, Ming-Wei Chang, Xiaodong He, Wen-tau Yih

Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e.g., answers), search for good candidate semantic parses, and (2) choose the best model update algorithm. We propose effective and general solutions to each of them. Using policy shaping, we bias the search procedure towards semantic parses that are more compatible to the text, which provide better supervision signals for training. In addition, we propose an update equation that generalizes three different families of learning algorithms, which enables fast model exploration. When experimented on a recently proposed sequential question answering dataset, our framework leads to a new state-of-the-art model that outperforms previous work by 5.0% absolute on exact match accuracy.

📄 PDF Abstract BibTeX arXiv:1809.01299

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringSemantic Parsing

Similar Papers 제목 키워드 기반

Action-Dependent Optimality-Preserving Reward Shaping

2025-05-19 · Grant C. Forbes, JianXun Wang, Leonardo Villalobos-Arias, Arnav Jhala 외

Recent RL research has utilized reward shaping--particularly complex shaping rewards such as intrinsic motivation (IM)--to encourage agent exploration in sparse-reward environments. While often effective, ``reward hackin…

Montezuma's Revenge

On Generalized Bellman Equations and Temporal-Difference Learning

2017-04-14 · Huizhen Yu, A. Rupam Mahmood, Richard S. Sutton

We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without exec…

Generalized Fitted Q-Iteration with Clustered Data

2025-10-04 · Liyuan Hu, Jitao Wang, Zhenke Wu, Chengchun Shi arxiv

This paper focuses on reinforcement learning (RL) with clustered data, which is commonly encountered in healthcare applications. We propose a generalized fitted Q-iteration (FQI) algorithm that incorporates generalized e…

Reinforcement Learning

Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schrödinger Bridge

2026-03-23 · Yuehu Gong, Zeyuan Wang, Yulin Chen, Shutong Ding 외 arxiv

Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically instantiated with simple Gaussian policies …

Reinforcement Learning

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping

2026-05-11 · Haoyuan Sun, Jing Wang, Yuxin Song, Yu Lu 외 arxiv

Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) mo…

Reinforcement Learning