اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLearning to Navigate the Web
181
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agents learning through trial-and-error. For instance, following natural language instructions on the Web (such as booking a flight ticket) leads to RL settings where input vocabulary and number of actionable elements on a page can grow very large. Even though recent approaches improve the success rate on relatively simple environments with the help of human demonstrations to guide the exploration, they still fail in environments where the set of possible instructions can reach millions. We approach the aforementioned problems from a different perspective and propose guided RL approaches that can generate unbounded amount of experience for an agent to learn from. Instead of learning from a complicated instruction with a large vocabulary, we decompose it into multiple sub-instructions and schedule a curriculum in which an agent is tasked with a gradually increasing subset of these relatively easier sub-instructions. In addition, when the expert demonstrations are not available, we propose a novel meta-learning framework that generates new instruction following tasks and trains the agent more effectively. We train DQN, deep reinforcement learning agent, with Q-value function approximated with a novel QWeb neural network architecture on these smaller, synthetic instructions. We evaluate the ability of our agent to generalize to new instructions on World of Bits benchmark, on forms with up to 100 elements, supporting 14 million possible instructions. The QWeb agent outperforms the baseline without using any human demonstration achieving 100% success rate on several difficult environments.
قيم البحث
اقرأ أيضاً
Learning to autonomously navigate the web is a difficult sequential decision making task. The state and action spaces are large and combinatorial in nature, and websites are dynamic environments consisting of several pages. One of the bottlenecks of
training web navigation agents is providing a learnable curriculum of training environments that can cover the large variety of real-world websites. Therefore, we propose using Adversarial Environment Generation (AEG) to generate challenging web environments in which to train reinforcement learning (RL) agents. We provide a new benchmarking environment, gMiniWoB, which enables an RL adversary to use compositional primitives to learn to generate arbitrarily complex websites. To train the adversary, we propose a new technique for maximizing regret using the difference in the scores obtained by a pair of navigator agents. Our results show that our approach significantly outperforms prior methods for minimax regret AEG. The regret objective trains the adversary to design a curriculum of environments that are just-the-right-challenge for the navigator agents; our results show that over time, the adversary learns to generate increasingly complex web navigation tasks. The navigator agents trained with our technique learn to complete challenging, high-dimensional web navigation tasks, such as form filling, booking a flight etc. We show that the navigator agent trained with our proposed Flexible b-PAIRED technique significantly outperforms competitive automatic curriculum generation baselines -- including a state-of-the-art RL web navigation approach -- on a set of challenging unseen test environments, and achieves more than 80% success rate on some tasks.
Continual learning systems will interact with humans, with each other, and with the physical world through time -- and continue to learn and adapt as they do. An important open problem for continual learning is a large-scale benchmark that enables re
alistic evaluation of algorithms. In this paper, we study a natural setting for continual learning on a massive scale. We introduce the problem of personalized online language learning (POLL), which involves fitting personalized language models to a population of users that evolves over time. To facilitate research on POLL, we collect massive datasets of Twitter posts. These datasets, Firehose10M and Firehose100M, comprise 100 million tweets, posted by one million users over six years. Enabled by the Firehose datasets, we present a rigorous evaluation of continual learning algorithms on an unprecedented scale. Based on this analysis, we develop a simple algorithm for continual gradient descent (ConGraD) that outperforms prior continual learning methods on the Firehose datasets as well as earlier benchmarks. Collectively, the POLL problem setting, the Firehose datasets, and the ConGraD algorithm enable a complete benchmark for reproducible research on web-scale continual learning.
Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models. However, current generative approaches exhibit a significant challenge as they do not ensure t
hat the proposed molecular structures can be feasibly synthesized nor do they provide the synthesis routes of the proposed small molecules, thereby seriously limiting their practical applicability. In this work, we propose a novel forward synthesis framework powered by reinforcement learning (RL) for de novo drug design, Policy Gradient for Forward Synthesis (PGFS), that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo drug design system. In this setup, the agent learns to navigate through the immense synthetically accessible chemical space by subjecting commercially available small molecule building blocks to valid chemical reactions at every time step of the iterative virtual multi-step synthesis process. The proposed environment for drug discovery provides a highly challenging test-bed for RL algorithms owing to the large state space and high-dimensional continuous action space with hierarchical actions. PGFS achieves state-of-the-art performance in generating structures with high QED and penalized clogP. Moreover, we validate PGFS in an in-silico proof-of-concept associated with three HIV targets. Finally, we describe how the end-to-end training conceptualized in this study represents an important paradigm in radically expanding the synthesizable chemical space and automating the drug discovery process.
Learning to read words aloud is a major step towards becoming a reader. Many children struggle with the task because of the inconsistencies of English spelling-sound correspondences. Curricula vary enormously in how these patterns are taught. Childre
n are nonetheless expected to master the system in limited time (by grade 4). We used a cognitively interesting neural network architecture to examine whether the sequence of learning trials could be structured to facilitate learning. This is a hard combinatorial optimization problem even for a modest number of learning trials (e.g., 10K). We show how this sequence optimization problem can be posed as optimizing over a time varying distribution i.e., defining probability distributions over words at different steps in training. We then use stochastic gradient descent to find an optimal time-varying distribution and a corresponding optimal training sequence. We observed significant improvement on generalization accuracy compared to baseline conditions (random sequences; sequences biased by word frequency). These findings suggest an approach to improving learning outcomes in domains where performance depends on ability to generalize beyond limited training experience.
Knowledge is captured in the form of entities and their relationships and stored in knowledge graphs. Knowledge graphs enhance the capabilities of applications in many different areas including Web search, recommendation, and natural language underst
anding. This is mainly because, entities enable machines to understand things that go beyond simple tokens. Many modern algorithms use learned entity embeddings from these structured representations. However, building a knowledge graph takes time and effort, hence very costly and nontrivial. On the other hand, many Web sources describe entities in some structured format and therefore, finding ways to get them into useful entity knowledge is advantageous. We propose an approach that processes entity centric textual knowledge sources to learn entity embeddings and in turn avoids the need for a traditional knowledge graph. We first extract triples into the new representation format that does not use traditional complex triple extraction methods defined by pre-determined relationship labels. Then we learn entity embeddings through this new type of triples. We show that the embeddings learned from our approach are: (i) high quality and comparable to a known knowledge graph-based embeddings and can be used to improve them further, (ii) better than a contextual language model-based entity embeddings, and (iii) easy to compute and versatile in domain-specific applications where a knowledge graph is not readily available
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
