Deep reinforcement learning (RL) has achieved superhuman performance in problems ranging from data center cooling to video games. RL policies may soon be widely deployed, with research underway in autonomous driving, negotiation and automated trading. Many potential applications are safety-critical: automated trading failures caused Knight Capital to lose USD 460M, while faulty autonomous vehicles have resulted in loss of life. Consequently, it is critical that RL policies are robust: both to naturally occurring distribution shift, and to malicious attacks by adversaries. Unfortunately, we find that RL policies which perform at a high-level in normal situations can harbor serious vulnerabilities which can be exploited by an adversary. Prior work has shown deep RL policies are vulnerable to small adversarial perturbations to their observations, similar to adversarial examples in image classifiers.

We consider the optimization of distributed resource scheduling to minimize the sum of task latency and energy consumption for all the Internet of things devices (IoTDs) in a large-scale mobile edge computing (MEC) system. To address this problem, we propose a distributed intelligent resource scheduling (DIRS) framework, which includes centralized training relying on the global information and distributed decision making by each agent deployed in each MEC server. More specifically, we first introduce a novel multi-agent ensemble-assisted distributed deep reinforcement learning (DRL) architecture, which can simplify the overall neural network structure of each agent by partitioning the state space and also improve the performance of a single agent by combining decisions of all the agents. Secondly, we apply action refinement to enhance the exploration ability of the proposed DIRS framework, where the near-optimal state-action pairs are obtained by a novel L\'evy flight search. Finally, an imitation acceleration scheme is presented to pre-train all the agents, which can significantly accelerate the learning process of the proposed framework through learning the professional experience from a small amount of demonstration data. Extensive simulations are conducted to demonstrate that the proposed DIRS framework is efficient and outperforms the existing benchmark schemes.

Personalization is very powerful in improving the effectiveness of health interventions. Reinforcement learning (RL) algorithms are suitable for learning these tailored interventions from sequential data collected about individuals. However, learning can be very fragile. The time to learn intervention policies is limited as disengagement from the user can occur quickly. Also, in e-Health intervention timing can be crucial before the optimal window passes. We present an approach that learns tailored personalization policies for groups of users by combining RL and clustering. The benefits are two-fold: speeding up the learning to prevent disengagement while maintaining a high level of personalization. Our clustering approach utilizes dynamic time warping to compare user trajectories consisting of states and rewards. We apply online and batch RL to learn policies over clusters of individuals and introduce our self-developed and publicly available simulator for e-Health interventions to evaluate our approach. We compare our methods with an e-Health intervention benchmark. We demonstrate that batch learning outperforms online learning for our setting. Furthermore, our proposed clustering approach for RL finds near-optimal clusterings which lead to significantly better policies in terms of cumulative reward compared to learning a policy per individual or learning one non-personalized policy across all individuals. Our findings also indicate that the learned policies accurately learn to send interventions at the right moments and that the users workout more and at the right times of the day.

Locomotion is a prime example for adaptive behavior in animals and biological control principles have inspired control architectures for legged robots. While machine learning has been successfully applied to many tasks in recent years, Deep Reinforcement Learning approaches still appear to struggle when applied to real world robots in continuous control tasks and in particular do not appear as robust solutions that can handle uncertainties well. Therefore, there is a new interest in incorporating biological principles into such learning architectures. While inducing a hierarchical organization as found in motor control has shown already some success, we here propose a decentralized organization as found in insect motor control for coordination of different legs. A decentralized and distributed architecture is introduced on a simulated hexapod robot and the details of the controller are learned through Deep Reinforcement Learning. We first show that such a concurrent local structure is able to learn better walking behavior. Secondly, that the simpler organization is learned faster compared to holistic approaches.

Machine learning, task automation and robotics are already widely used in business. These and other AI technologies are about to multiply, and we look at how organizations can best take advantage of them. COVID-19 disruption has left enterprises with no choice but to reassess digital transformation investments and roadmaps. While less important projects are delayed, transformation projects involving AI and automation are receiving a lot of attention right now. In just the last 60 days, the adoption of varying levels of AI technologies across the enterprise surged with an incredible sense of urgency.

This paper introduced a reinforcement learning based decision support system in textile manufacturing process. A solution optimization problem of color fading ozonation is discussed and set up as a Markov Decision Process (MDP) in terms of tuple {S, A, P, R}. Q-learning is used to train an agent in the interaction with the setup environment by accumulating the reward R. According to the application result, it is found that the proposed MDP model has well expressed the optimization problem of textile manufacturing process discussed in this paper, therefore the use of reinforcement learning to support decision making in this sector is conducted and proven that is applicable with promising prospects.

Mixed integer linear programs are commonly solved by Branch and Bound algorithms. A key factor of the efficiency of the most successful commercial solvers is their fine-tuned heuristics. In this paper, we leverage patterns in real-world instances to learn from scratch a new branching strategy optimised for a given problem and compare it with a commercial solver. We propose FMSTS, a novel Reinforcement Learning approach specifically designed for this task. The strength of our method lies in the consistency between a local value function and a global metric of interest. In addition, we provide insights for adapting known RL techniques to the Branch and Bound setting, and present a new neural network architecture inspired from the literature. To our knowledge, it is the first time Reinforcement Learning has been used to fully optimise the branching strategy. Computational experiments show that our method is appropriate and able to generalise well to new instances.

In this paper, we propose the use of traditional animations, heuristic behavior and reinforcement learning in the creation of intelligent characters for computational media. The traditional animation and heuristic gives artistic control over the behavior while the reinforcement learning adds generalization. The use case presented is a dog character with a high-level controller in a 3D environment which is built around the desired behaviors to be learned, such as fetching an item. As the development of the environment is the key for learning, further analysis is conducted of how to build those learning environments, the effects of environment and agent modeling choices, training procedures and generalization of the learned behavior. This analysis builds insight of the aforementioned factors and may serve as guide in the development of environments in general.

It is useful, for the forthcoming discussion, to have a better understanding of some key terms used in RL. Agent: A software/hardware mechanism which takes certain action depending on its interaction with the surrounding environment; for example, a drone making a delivery, or Super Mario navigating a video game. The algorithm is the agent. Action: An action is one of all the possible moves the agent can make. An action is almost self-explanatory, but it should be noted that agents usually choose from a list of discrete possible actions.

Spoken dialog systems have seen applications in many domains, including medical for automatic conversational diagnosis. State-of-the-art dialog managers are usually driven by deep reinforcement learning models, such as deep Q networks (DQNs), which learn by interacting with a simulator to explore the entire action space since real conversations are limited. However, the DQN-based automatic diagnosis models do not achieve satisfying performances when adapted to new, unseen diseases with only a few training samples. In this work, we propose the Prototypical Q Networks (ProtoQN) as the dialog manager for the automatic diagnosis systems. The model calculates prototype embeddings with real conversations between doctors and patients, learning from them and simulator-augmented dialogs more efficiently. We create both supervised and few-shot learning tasks with the Muzhi corpus. Experiments showed that the ProtoQN significantly outperformed the baseline DQN model in both supervised and few-shot learning scenarios, and achieves state-of-the-art few-shot learning performances.