Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness through disturbing the current state or simulating environmental parameters in a heuristic way, which lack quantified robustness to the system dynamics (i.e. transition probability). To overcome this issue, we leverage Wasserstein distance to measure the disturbance to the reference transition kernel. With Wasserstein distance, we are able to connect transition kernel disturbance to the state disturbance, i.e. reduce an infinite-dimensional optimization problem to a finite-dimensional risk-aware problem. Through the derived risk-aware optimal Bellman equation, we show the existence of optimal robust policies, provide a sensitivity analysis for the perturbations, and then design a novel robust learning algorithm--Wasserstein Robust Advantage Actor-Critic algorithm (WRAAC). The effectiveness of the proposed algorithm is verified in the Cart-Pole environment.

Adversarial examples are firstly investigated in the area of computer vision: by adding some carefully designed ''noise'' to the original input image, the perturbed image that cannot be distinguished from the original one by human, can fool a well-trained classifier easily. In recent years, researchers also demonstrated that adversarial examples can mislead deep reinforcement learning (DRL) agents on playing video games using image inputs with similar methods. However, although DRL has been more and more popular in the area of intelligent transportation systems, there is little research investigating the impacts of adversarial attacks on them, especially for algorithms that do not take images as inputs. In this work, we investigated several fast methods to generate adversarial examples to significantly degrade the performance of a well-trained DRL- based energy management system of an extended range electric delivery vehicle. The perturbed inputs are low-dimensional state representations and close to the original inputs quantified by different kinds of norms. Our work shows that, to apply DRL agents on real-world transportation systems, adversarial examples in the form of cyber-attack should be considered carefully, especially for applications that may lead to serious safety issues.

Coverage path planning is a well-studied problem in robotics in which a robot must plan a path that passes through every point in a given area repeatedly, usually with a uniform frequency. To address the scenario in which some points need to be visited more frequently than others, this problem has been extended to non-uniform coverage planning. This paper considers the variant of non-uniform coverage in which the robot does not know the distribution of relevant events beforehand and must nevertheless learn to maximize the rate of detecting events of interest. This continual area sweeping problem has been previously formalized in a way that makes strong assumptions about the environment, and to date only a greedy approach has been proposed. We generalize the continual area sweeping formulation to include fewer environmental constraints, and propose a novel approach based on reinforcement learning in a Semi-Markov Decision Process. This approach is evaluated in an abstract simulation and in a high fidelity Gazebo simulation. These evaluations show significant improvement upon the existing approach in general settings, which is especially relevant in the growing area of service robotics.

In this advanced course on deep reinforcement learning, you will learn how to implement policy gradient, actor critic, deep deterministic policy gradient (DDPG), and twin delayed deep deterministic policy gradient (TD3) algorithms in a variety of challenging environments from the Open AI gym. From there we will progress to teaching an agent to balance the cart pole using Q learning. After mastering the fundamentals, the pace quickens, and we move straight into an introduction to policy gradient methods. We cover the REINFORCE algorithm, and use it to teach an artificial intelligence to land on the moon in the lunar lander environment from the Open AI gym. Next we progress to coding up the one step actor critic algorithm, to again beat the lunar lander.

Despite its notable success in adversarial learning approaches to multi-domain task-oriented dialog system, training the dialog policy via adversarial inverse reinforcement learning often fails to balance the performance of the policy generator and reward estimator. During optimization, the reward estimator often overwhelms the policy generator and produces excessively uninformative gradients. We proposes the Variational Reward estimator Bottleneck (VRB), which is an effective regularization method that aims to constrain unproductive information flows between inputs and the reward estimator. The VRB focuses on capturing discriminative features, by exploiting information bottleneck on mutual information. Empirical results on a multi-domain task-oriented dialog dataset demonstrate that the VRB significantly outperforms previous methods.

There has been an increasing surge of interest on development of advanced Reinforcement Learning (RL) systems as intelligent approaches to learn optimal control policies directly from smart agents' interactions with the environment. Objectives: In a model-free RL method with continuous state-space, typically, the value function of the states needs to be approximated. In this regard, Deep Neural Networks (DNNs) provide an attractive modeling mechanism to approximate the value function using sample transitions. DNN-based solutions, however, suffer from high sensitivity to parameter selection, are prone to overfitting, and are not very sample efficient. A Kalman-based methodology, on the other hand, could be used as an efficient alternative. Such an approach, however, commonly requires a-priori information about the system (such as noise statistics) to perform efficiently. The main objective of this paper is to address this issue. Methods: As a remedy to the aforementioned problems, this paper proposes an innovative Multiple Model Kalman Temporal Difference (MM-KTD) framework, which adapts the parameters of the filter using the observed states and rewards. Moreover, an active learning method is proposed to enhance the sampling efficiency of the system. More specifically, the estimated uncertainty of the value functions are exploited to form the behaviour policy leading to more visits to less certain values, therefore, improving the overall learning sample efficiency. As a result, the proposed MM-KTD framework can learn the optimal policy with significantly reduced number of samples as compared to its DNN-based counterparts. Results: To evaluate performance of the proposed MM-KTD framework, we have performed a comprehensive set of experiments based on three RL benchmarks. Experimental results show superiority of the MM-KTD framework in comparison to its state-of-the-art counterparts.

Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. It promises the user services at large scale and low cost while eliminating the need for infrastructure management. On cloud provider side, flexible resource management is required to meet fluctuating demand. It can be enabled through automated provisioning and deprovisioning of resources. A common approach among both commercial and open source serverless computing platforms is workload-based auto-scaling, where a designated algorithm scales instances according to the number of incoming requests. In the recently evolving serverless framework Knative a request-based policy is proposed, where the algorithm scales resources by a configured maximum number of requests that can be processed in parallel per instance, the so-called concurrency. As we show in a baseline experiment, this predefined concurrency level can strongly influence the performance of a serverless application. However, identifying the concurrency configuration that yields the highest possible quality of service is a challenging task due to various factors, e.g. varying workload and complex infrastructure characteristics, influencing throughput and latency. While there has been considerable research into intelligent techniques for optimizing auto-scaling for virtual machine provisioning, this topic has not yet been discussed in the area of serverless computing. For this reason, we investigate the applicability of a reinforcement learning approach, which has been proven on dynamic virtual machine provisioning, to request-based auto-scaling in a serverless framework. Our results show that within a limited number of iterations our proposed model learns an effective scaling policy per workload, improving the performance compared to the default auto-scaling configuration.

With advances in reinforcement learning (RL), agents are now being developed in high-stakes application domains such as healthcare and transportation. Explaining the behavior of these agents is challenging, as the environments in which they act have large state spaces, and their decision-making can be affected by delayed rewards, making it difficult to analyze their behavior. To address this problem, several approaches have been developed. Some approaches attempt to convey the $\textit{global}$ behavior of the agent, describing the actions it takes in different states. Other approaches devised $\textit{local}$ explanations which provide information regarding the agent's decision-making in a particular state. In this paper, we combine global and local explanation methods, and evaluate their joint and separate contributions, providing (to the best of our knowledge) the first user study of combined local and global explanations for RL agents. Specifically, we augment strategy summaries that extract important trajectories of states from simulations of the agent with saliency maps which show what information the agent attends to. Our results show that the choice of what states to include in the summary (global information) strongly affects people's understanding of agents: participants shown summaries that included important states significantly outperformed participants who were presented with agent behavior in a randomly set of chosen world-states. We find mixed results with respect to augmenting demonstrations with saliency maps (local information), as the addition of saliency maps did not significantly improve performance in most cases. However, we do find some evidence that saliency maps can help users better understand what information the agent relies on in its decision making, suggesting avenues for future work that can further improve explanations of RL agents.

Framed in positive terms, this report examines how technical AI research might be steered in a manner that is more attentive to humanity's long-term prospects for survival as a species. In negative terms, we ask what existential risks humanity might face from AI development in the next century, and by what principles contemporary technical research might be directed to address those risks. A key property of hypothetical AI technologies is introduced, called \emph{prepotence}, which is useful for delineating a variety of potential existential risks from artificial intelligence, even as AI paradigms might shift. A set of \auxref{dirtot} contemporary research \directions are then examined for their potential benefit to existential safety. Each research direction is explained with a scenario-driven motivation, and examples of existing work from which to build. The research directions present their own risks and benefits to society that could occur at various scales of impact, and in particular are not guaranteed to benefit existential safety if major developments in them are deployed without adequate forethought and oversight. As such, each direction is accompanied by a consideration of potentially negative side effects.

Whether it's a dog chasing after a ball, or a monkey swinging through the trees, animals can effortlessly perform an incredibly rich repertoire of agile locomotion skills. But designing controllers that enable legged robots to replicate these agile behaviors can be a very challenging task. The superior agility seen in animals, as compared to robots, might lead one to wonder: can we create more agile robotic controllers with less effort by directly imitating animals? In this work, we present a framework for learning robotic locomotion skills by imitating animals. Given a reference motion clip recorded from an animal (e.g. a dog), our framework uses reinforcement learning to train a control policy that enables a robot to imitate the motion in the real world.