Chris Wiggins is an associate professor of applied mathematics at Columbia University and the Chief Data Scientist at The New York Times. At Columbia he is a founding member of the executive committee of the Data Science Institute, and of the Department of Applied Physics and Applied Mathematics as well as the Department of Systems Biology, and is affiliated faculty in Statistics. The Data Science group at The New York Times develops and deploys machine learning solutions to newsroom and business problems. Re-framing real-world questions as machine learning tasks require not only adapting and extending models and algorithms to new or special cases but also sufficient breadth to know the right method for the right challenge. The speaker will first outline how unsupervised, supervised, and reinforcement learning methods are increasingly used in human applications for description, prediction, and prescription, respectively.

The demand for people with knowledge and skills in artificial intelligence (AI) and machine learning (ML) hugely outstrips the supply. This means that learning and gaining qualifications in these subjects can be a great way to enhance your career prospects. However, not everyone has the spare time and money to spend years studying for a degree or other formal qualifications. Today, with the wealth of freely available educational content online, it may not be necessary. There are so many courses, tutorials, and guides available online that it is perfectly possible to gain a thorough grounding in these subjects without paying a penny.

A novel deep multi-agent reinforcement learning framework is proposed to identify and resolve conflicts among a variable number of aircraft in a high-density, stochastic, and dynamic sector in en route airspace. Currently the sector capacity is limited by human air traffic controller's cognitive limitation. In order to scale up to a high-density airspace, in this work we investigate the feasibility of a new concept (autonomous separation assurance) and a new approach (multi-agent reinforcement learning) to push the sector capacity above human cognitive limitation. We propose the concept of using distributed vehicle autonomy to ensure separation, instead of a centralized sector air traffic controller. Our proposed framework utilizes an actor-critic model, Proximal Policy Optimization (PPO) that we customize to incorporate an attention network. By using the attention network, we are able to encode the information from a variable number of intruder aircraft into a fixed length vector and allow the agents to learn which intruder aircraft's information is critical to achieve the optimal performance. This allows the agents to have access to variable aircraft information in the sector in a scalable, efficient approach to achieve high traffic throughput under uncertainty. The agents are trained using a centralized learning, decentralized execution scheme where one neural network is learned and shared by all agents in the environment. To validate the proposed framework, we designed three challenging case studies in the BlueSky air traffic control environment. Numerical results show the proposed framework significantly reduces the offline training time without sacrificing performance.

Autonomous Vehicles (AVs) with Deep Reinforcement Learning (DRL)-based controllers are used for reducing traffic jams. AVs trained with such deep neural networks render them vulnerable to machine learning-based attacks. In this work, we explore the backdooring of a DRL-based AV controller in a standard traffic scenario. The AV exhibits intended operation of reducing congestion during genuine observations, but when a particular set of observations appears, the AV can be triggered to either decelerate to cause congestion (congestion attack) or to accelerate and crash into the vehicle in front (insurance attack). These backdoors in AVs may be engineered to pose serious threats to human lives.

Artificial Intelligence has historically relied on planning, heuristics, and handcrafted approaches designed by experts. All the while claiming to pursue the creation of Intelligence. This approach fails to acknowledge that intelligence emerges from the dynamics within a complex system. Neurons in the brain are governed by local rules, where no single neuron, or group of neurons, coordinates or controls the others. This local structure gives rise to the appropriate dynamics in which intelligence can emerge. Populations of neurons must compete with their neighbors for resources, inhibition, and activity representation. At the same time, they must cooperate, so the population and organism can perform high-level functions. To this end, we introduce modeling neurons as reinforcement learning agents. Where each neuron may be viewed as an independent actor, trying to maximize its own self-interest. By framing learning in this way, we open the door to an entirely new approach to building intelligent systems.

The demand for people with knowledge and skills in artificial intelligence (AI) and machine learning (ML) hugely outstrips the supply. This means that learning and gaining qualifications in these subjects can be a great way to enhance your career prospects. However, not everyone has the spare time and money to spend years studying for a degree or other formal qualifications. Today, with the wealth of freely available educational content online, it may not be necessary. There are so many courses, tutorials, and guides available online that it is perfectly possible to gain a thorough grounding in these subjects without paying a penny.

The growth of reinforcement learning as a tool of machine learning has been the last option in industry usage to solve complex problems that are rising every day with changing market dynamics. With increasing intelligent systems, reinforcement learning for industrial applications is unfolding advanced intelligent solutions to tackle complex problems. Industries are significantly realizing the importance of reinforcement learning in their operations which help them in for being more customer-centric. The future goal of industries using reinforcement learning would be a 100 % return on investment. Please connect with us if you resonate with our article.

The goal of this challenge is to test the potential of Reinforcement Learning (RL) to control electrical power transmission, in the most cost-effective manner, while keeping people and equipment safe from harm. Solving this challenge may have very positive impacts on society, as governments move to decarbonize the electricity sector and to electrify other sectors, to help reach IPCC climate goals. Existing software, computational methods and optimal powerflow solvers are not adequate for real-time network operations on short temporal horizons in a reasonable computational time. With recent changes in electricity generation and consumption patterns, system operation is moving to become more of a stochastic rather than a deterministic control problem. In order to overcome these complexities, new computational methods are required. The intention of this challenge is to explore RL as a solution method for electricity network control. There may be under-utilized, cost-effective flexibility in the power network that RL techniques can identify and capitalize on, that human operators and traditional solution techniques are unaware of or unaccustomed to. An RL agent that can act in conjunction, or in parallel with human network operators, will optimize grid security and reliability, allowing more renewable resources to be connected while minimizing the cost and maintaining supply to customers, and preventing damage to electrical equipment. Another aim of the project is to broaden the audience for the problem of electricity network control and to foster collaboration between experts in both the power systems community and the wider RL/ML community.

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms. Theory-inspired simulations show that the widely-used temporal difference (TD) algorithm is strictly suboptimal when evaluated in a non-asymptotic setting, even when combined with Polyak-Ruppert iterate averaging. We remedy this issue by introducing and analyzing variance-reduced forms of stochastic approximation, showing that they achieve non-asymptotic, instance-dependent optimality up to logarithmic factors.

Deep reinforcement learning can learn effective policies for a wide range of tasks, but is notoriously difficult to use due to instability and sensitivity to hyperparameters. The reasons for this remain unclear. When using standard supervised methods (e.g., for bandits), on-policy data collection provides "hard negatives" that correct the model in precisely those states and actions that the policy is likely to visit. We call this phenomenon "corrective feedback." We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from this corrective feedback, and training on the experience collected by the algorithm is not sufficient to correct errors in the Q-function. In fact, Q-learning and related methods can exhibit pathological interactions between the distribution of experience collected by the agent and the policy induced by training on that experience, leading to potential instability, sub-optimal convergence, and poor results when learning from noisy, sparse or delayed rewards. We demonstrate the existence of this problem, both theoretically and empirically. We then show that a specific correction to the data distribution can mitigate this issue. Based on these observations, we propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training, resulting in substantial improvements in a range of challenging RL settings, such as multi-task learning and learning from noisy reward signals. Blog post presenting a summary of this work is available at: https://bair.berkeley.edu/blog/2020/03/16/discor/.