Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeuro-Symbolic Reinforcement Learning with First-Order Logic
التعلم التعزيز الرمز العصبي الرمزي مع منطق من الدرجة الأولى
350
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما تتطلب طرق تعلم التعلم العميق (RL) العديد من التجارب قبل التقارب، ولا يتم توفير إمكانية التفسير المباشر للسياسات المدربة.من أجل تحقيق التقارب السريع والتفسيرية للسياسة في RL، نقترح طريقة RL رواية للألعاب القائمة على النصوص مع إطار عمل رمزي مؤخرا يسمى الشبكة العصبية المنطقية، والتي يمكن أن تتعلم القواعد الرمزية والتفسيرية في شبكتها المختلفة.الطريقة الأولى لاستخراج الحقائق المنطقية من الدرجة الأولى من مراقبة النص وشبكة معنى الكلمة الخارجية (Congernet)، ثم قم بتدريب سياسة في الشبكة مع مشغلين منطقي قابل التفسير مباشرة.تظهر النتائج التجريبية لدينا التدريب RL مع الأسلوب المقترح بشكل أسرع بكثير من الأساليب الخلية العصبية الأخرى في مؤشر TextWorld.
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with directly interpretable logical operators. Our experimental results show RL training with the proposed method converges significantly faster than other state-of-the-art neuro-symbolic methods in a TextWorld benchmark.
References used
https://aclanthology.org/
rate research
Read More
First-order meta-learning algorithms have been widely used in practice to learn initial model parameters that can be quickly adapted to new tasks due to their efficiency and effectiveness. However, existing studies find that meta-learner can overfit
to some specific adaptation when we have heterogeneous tasks, leading to significantly degraded performance. In Natural Language Processing (NLP) applications, datasets are often diverse and each task has its unique characteristics. Therefore, to address the overfitting issue when applying first-order meta-learning to NLP applications, we propose to reduce the variance of the gradient estimator used in task adaptation. To this end, we develop a variance-reduced first-order meta-learning algorithm. The core of our algorithm is to introduce a novel variance reduction term to the gradient estimation when performing the task adaptation. Experiments on two NLP applications: few-shot text classification and multi-domain dialog state tracking demonstrate the superior performance of our proposed method.
Recently, language models (LMs) have achieved significant performance on many NLU tasks, which has spurred widespread interest for their possible applications in the scientific and social area. However, LMs have faced much criticism of whether they a
re truly capable of reasoning in NLU. In this work, we propose a diagnostic method for first-order logic (FOL) reasoning with a new proposed benchmark, LogicNLI. LogicNLI is an NLI-style dataset that effectively disentangles the target FOL reasoning from commonsense inference and can be used to diagnose LMs from four perspectives: accuracy, robustness, generalization, and interpretability. Experiments on BERT, RoBERTa, and XLNet, have uncovered the weaknesses of these LMs on FOL reasoning, which motivates future exploration to enhance the reasoning ability.
We present a system for learning generalized, stereotypical patterns of events---or schemas''---from natural language stories, and applying them to make predictions about other stories. Our schemas are represented with Episodic Logic, a logical form
that closely mirrors natural language. By beginning with a head start'' set of protoschemas--- schemas that a 1- or 2-year-old child would likely know---we can obtain useful, general world knowledge with very few story examples---often only one or two. Learned schemas can be combined into more complex, composite schemas, and used to make predictions in other stories where only partial information is available.
It is challenging to design profitable and practical trading strategies, as stock price movements are highly stochastic, and the market is heavily influenced by chaotic data across sources like news and social media. Existing NLP approaches largely t
reat stock prediction as a classification or regression problem and are not optimized to make profitable investment decisions. Further, they do not model the temporal dynamics of large volumes of diversely influential text to which the market responds quickly. Building on these shortcomings, we propose a deep reinforcement learning approach that makes time-aware decisions to trade stocks while optimizing profit using textual data. Our method outperforms state-of-the-art in terms of risk-adjusted returns in trading simulations on two benchmarks: Tweets (English) and financial news (Chinese) pertaining to two major indexes and four global stock markets. Through extensive experiments and studies, we build the case for our method as a tool for quantitative trading.
Timeline Summarisation (TLS) aims to generate a concise, time-ordered list of events described in sources such as news articles. However, current systems do not provide an adequate way to adapt to new domains nor to focus on the aspects of interest t
o a particular user. Therefore, we propose a method for interactively learning abstractive TLS using Reinforcement Learning (RL). We define a compound reward function and use RL to fine-tune an abstractive Multi-document Summarisation (MDS) model, which avoids the need to train using reference summaries. One of the sub-reward functions will be learned interactively from user feedback to ensure the consistency between users' demands and the generated timeline. The other sub-reward functions contribute to topical coherence and linguistic fluency. We plan experiments to evaluate whether our approach could generate accurate and precise timelines tailored for each user.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
