Shipra Agrawal, seated at a desk with a hot beverage
Shipra Agrawal, Amazon Scholar and assistant professor in Columbia University’s Industrial Engineering and Operations Research Department.

NeurIPS: Shipra Agrawal on the appeal of reinforcement learning

This Amazon Scholar’s work spans two of the most popular topics at the most popular AI conference: reinforcement learning and bandit problems.

As deep neural networks have come to dominate AI, the Conference on Neural Information Processing Systems (NeurIPS 2020) has become the most popular conference in the field.

And at the most popular conference in the field, one of the most popular topics is reinforcement learning: at this year’s NeurIPS, 95 accepted papers use the term in their titles.

“Reinforcement learning is very, very powerful, because you can kind of learn anything, adaptively from the feedback, and by exploring the decision space,” says Shipra Agrawal, an Amazon Scholar, an assistant professor in Columbia University’s Industrial Engineering and Operations Research Department, and an area chair at NeurIPS, who studies reinforcement learning. “In concept, it's very akin to how humans learn, by trial and error, and how they adapt to what they see — without requiring a loss function and so on, just by some kind of rewards or positive feedback.”

In reinforcement learning, an agent explores its environment, trying out different responses to different states of affairs, gradually learning a set of policies that will enable it to maximize some reward.

“Usually, when we say ‘classification’ or ‘regression’, it's a very specific pattern recognition problem, and then you have to think carefully about where you can apply it,” Agrawal says. “But when you say ‘reinforcement learning,’ at a high level, it's like, ‘Oh, I will just make some decisions, see some feedback, and then I'll change my decisions accordingly.’ That's it.

“But theoretically, it also has a lot of structure, which makes it possible to analyze it in a rigorous manner. So I think there's this unique combination of theoretical curiosity and practical potential that makes it very attractive. I teach a course on reinforcement learning [at Columbia], which is a PhD class of 40, and it usually has a waiting list of 100.”

Markov decision processes

What gives the problem of reinforcement learning its theoretical structure, Agrawal explains, is a model of sequential decision making called a Markov decision process (MDP). An MDP consists of a sequence of decisions, and each decision elicits feedback: if, for instance, the decision is what products to display on a shopping site, the feedback might be whether a customer buys one of the displayed products. 

Each new decision is based not only on the feedback to the previous decision but on the whole history of decisions and feedback that preceded it. That history is captured in a variable called the state.

“That makes the decision-making problem complex, because now you need to think not only about what decisions would generate good immediate feedback but also what decisions could take you to good states,” Agrawal says. “A decision may produce a good immediate reaction, but it may take the customer to a bad state later on. The Markov decision process is specified by the state transition model and the reward model, because both of them matter when you're deciding what is a good policy to make decisions.”

Framing the problem of reinforcement learning in terms of MDPs is straightforward, Agrawal says. “Just take MDP and say, ‘I don't know the state transition model, and I don't know the reward model, and I need to learn them from the feedback itself,” she says. “I can observe the state at the last time step, I know what the state is right now, and if I've seen enough of these transitions, I can infer what the state transition model must have been. In the same way, I can infer what the reward model must have been. The challenge is to combine this learning with the task of finding a good policy.”

MDPs have been studied since at least the 1950s. But, Agrawal says, “once you make machine learning a central feature in that problem, then suddenly, the goal shifts. How do I properly combine these two things? The initial solutions were based on a two-phase process: you learn the model first, and then you optimize it. But that doesn't scale. How well do you need to learn the model? You can figure out how well you need to learn it in the worst case, but that’s too much: you can't really learn the model that well, everywhere. And then you say, ‘Well, I don't need to learn it everywhere.’ Who cares what happens in some situation which is never going to occur or which I never really want to go into anyway? Conceptually, the problem becomes very, very different once you combine these two things.”

Explore/exploit

In her own work, Agrawal is exploring another trade-off posed by reinforcement learning: the explore-exploit dilemma. During reinforcement learning, the agent is trying to learn how to maximize some reward (exploration) — but it’s also trying to maximize the reward (exploitation). How does it decide when to risk an untried response that may provide useful information but may also reduce its reward?

The explore-exploit dilemma can be modeled as a bandit problem, named after the situation of a gambler trying to identify the one slot machine (one-armed bandit) among many with the highest average payout. Bandit problems are another popular topic at NeurIPS: the word “bandit” shows up in the titles of 45 accepted papers.

“A lot of my work is based on this idea of posterior sampling — Thompson sampling — which is a Bayesian way to do exploration/exploitation,” Agrawal says. “It's a theoretically rigorous method — you can prove guarantees on it — and at the same time, with posterior sampling, the cost of exploration is often as low as in some practically good, easy methods. So it kind of provides best of both worlds, at least in bandits. I'm very excited about taking these techniques and using them for reinforcement learning, especially for deep reinforcement learning.”

Learn more about Amazon researchers' involvement in NeurIPS 2020, the papers they're presenting, and the workshops that Amazon is sponsoring and that our researchers are organizing and attending, and sign up to participate in a virtual panel on fairness in AI on December 11.

Research areas

Related content

US, CA, Palo Alto
The Amazon Search team creates powerful, customer-focused search and advertising solutions and technologies. Whenever a customer visits an Amazon site worldwide and types in a query or browses through product categories, the Amazon Search services go to work. We design, develop, and deploy high performance, fault-tolerant distributed search systems used by millions of Amazon customers every day. Our team works to maximize the quality and effectiveness of the search experience for visitors to Amazon websites worldwide.
JP, Tokyo
The Amazon Logistics (AMZL) Team is responsible for the acquisition, design, construction, and management of all facilities in the Amazon Delivery Station Network. AMZL is looking for a talented and passionate Data Scientist to help shape its Last Mile business with technical strategies and solutions, by processing, analyzing and interpreting huge data sets. You should be comfortable with ambiguity, problem solving and enjoy working in a fast-paced, diverse and dynamic environment. Using analytical rigor and statistical methods, you mine through data to identify opportunities for Amazon and our delivery channels. And you collaborate with other scientists, engineers, Product and Program Managers to deploy new products and solutions. [More Information] Last Mile Department Data Analyst/BI Engineer Tokyo Office *Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, visit https://www.amazon.jobs/disability/jp Key job responsibilities Creating a roadmap of the most challenging business questions and use data to articulate possible root cause analysis and solutions Managing and executing entire projects or components of large projects from start to finish including project management, data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights Partnering with Product, Program and Engineering teams to design and run models, research new algorithms, and prove incrementality and drive growth Understanding drivers, impacts, and key influences on seller growth dynamics Developing and scaling end-to-end ML Models and solutions Automating feedback loops for algorithms in production Utilizing Amazon systems and tools to effectively work with terabytes of data About the team Last Mile Execution Analytics (LMEA) team of JP works as an integral part of Amazon Logistics to ensure that its business intelligence, analytics, tools and planning needs are met. By providing information, insight, and decision support, we strive to enable success of all parts of AMZL. Our customer set includes senior management, station operations, external vendors, long-term planning, Ops technology (Voice of the Delivery Station, Voice of the Customer), network planning, and pretty much every BI and Ops teams. Voice of Employee [Work Life Harmony] We believe, it is important to spend private time such as spending time with your family or doing anything you like to spur innovation. Amazon promotes a fulfilling and flexible work style according to the work volume and lifestyle of each employee.
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
LU, Luxembourg
Are you a talented and inventive scientist with a strong passion about modern data technologies and interested to improve business processes, extracting value from the data? Would you like to be a part of an organization that is aiming to use self-learning technology to process data in order to support the management of the procurement function? The Global Procurement Technology, as a part of Global Procurement Operations, is seeking a skilled Data Scientist to help build its future data intelligence in business ecosystem, working with large distributed systems of data and providing Machine Learning (ML) and Predictive Modeling expertise. You will be a member of the Data Engineering and ML Team, joining a fast-growing global organization, with a great vision to transform the Procurement field, and become the role model in the market. This team plays a strategic role supporting the core Procurement business domains as well as it is the cornerstone of any transformation and innovation initiative. Our mission is to provide a high-quality data environment to facilitate process optimization and business digitalization, on a global scale. We are supporting business initiatives, including but not limited to, strategic supplier sourcing (e.g. contracting, negotiation, spend analysis, market research, etc.), order management, supplier performance, etc. We are seeking an individual who can thrive in a fast-paced work environment, be collaborative and share knowledge and experience with his colleagues. You are expected to deliver results, but at the same time have fun with your teammates and enjoy working in the company. In Amazon, you will find all the resources required to learn new skills, grow your career, and become a better professional. You will connect with world leaders in your field and you will be tackling Data Science challenges to ensure business continuity, by taking the right decisions for your customers. As a Data Scientist in the team, you will: -be the subject matter expert to support team strategies that will take Global Procurement Operations towards world-class predictive maintenance practices and processes, driving more effective procurement functions, e.g. supplier segmentation, negotiations, shipping supplies volume forecast, spend management, etc. -have strong analytical skills and excel in the design, creation, management, and enterprise use of large data sets, combining raw data from different sources -provide technical expertise to support the development of ML models to facilitate intelligent digital services, such as Contract Lifecycle Management (CLM) and Negotiations platform -cooperate closely with different groups of stakeholders, e.g. data/software engineers, product/program managers, analysts, senior leadership, etc. to evaluate business needs and objectives to set up the best data management environment -create and share with audiences of varying levels technical papers and presentations -deal with ambiguity, prioritizing needs, and delivering results in a dynamic environment Basic qualifications -Master’s Degree in Computer Science/Engineering, Informatics, Mathematics, or a related technical discipline -3+ years of industry experience in data engineering/science, business intelligence or related field -3+ years experience in algorithm design, engineering and implementation for very-large scale applications to solve real problems -Very good knowledge of data modeling and evaluation -Very good understanding of regression modeling, forecasting techniques, time series analysis, machine-learning concepts such as supervised and unsupervised learning, classification, random forest, etc. -SQL and query performance tuning skills Preferred qualifications -2+ years of proficiency in using R, Python, Scala, Java or any modern language for data processing and statistical analysis -Experience with various RDBMS, such as PostgreSQL, MS SQL Server, MySQL, etc. -Experience architecting Big Data and ML solutions with AWS products (Redshift, DynamoDB, Lambda, S3, EMR, SageMaker, Lex, Kendra, Forecast etc.) -Experience articulating business questions and using quantitative techniques to arrive at a solution using available data -Experience with agile/scrum methodologies and its benefits of managing projects efficiently and delivering results iteratively -Excellent written and verbal communication skills including data visualization, especially in regards to quantitative topics discussed with non-technical colleagues
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, CA, San Francisco
About Twitch Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to world-class esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate, learn, and grow their personal interests and passions. We’re always live at Twitch. Stay up to date on all things Twitch on Linkedin, Twitter and on our Blog. About the role: Twitch builds data-driven machine learning solutions across several rich problem spaces: Natural Language Processing (NLP), Recommendations, Semantic Search, Classification/Categorization, Anomaly Detection, Forecasting, Safety, and HCI/Social Computing/Computational Social Science. As an Intern, you will work with a dedicated Mentor and Manager on a project in one of these problem areas. You will also be supported by an Advisor and participate in cohort activities such as research teach backs and leadership talks. This position can also be located in San Francisco, CA or virtual. You Will: Solve large-scale data problems. Design solutions for Twitch's problem spaces Explore ML and data research
US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in deep learning in the life sciences to solve real-world problems. As a Senior Applied Science Manager you will participate in developing exciting products for customers. Our team rewards curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the leading edge of both academic and applied research in this product area, you have the opportunity to work together with a diverse and talented team of scientists, engineers, and product managers and collaborate with others teams. Location is in Seattle, US Embrace Diversity Here at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust Balance Work and Life Our team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives Mentor & Grow Careers Our team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future. Key job responsibilities • Manage high performing engineering and science teams • Hire and develop top-performing engineers, scientists, and other managers • Develop and execute on project plans and delivery commitments • Work with business, data science, software engineer, biological, and product leaders to help define product requirements and with managers, scientists, and engineers to execute on them • Build and maintain world-class customer experience and operational excellence for your deliverables