This paper describes important considerations and challenges associated with online reinforcement-learning based waveform selection for target identification in frequency modulated continuous wave (FMCW) automotive radar systems. We present a novel learning approach based on satisficing Thompson sampling, which quickly identifies a waveform expected to yield satisfactory classification performance. We demonstrate through measurement-level simulations that effective waveform selection strategies can be quickly learned, even in cases where the radar must select from a large catalog of candidate waveforms. The radar learns to adaptively select a bandwidth for appropriate resolution and a slow-time unimodular code for interference mitigation in the scene of interest by optimizing an expected classification metric.

Reinforcement learning (RL) provides a (model-free) framework for learning-based control. RL problems aim at learning dynamics in the underlying data and finding optimal behaviors while collecting data via an interactive process. It differs from supervised learning that attempts to learn classification functions from labeled data, and unsupervised learning that seeks hidden patterns in unlabeled data. During the training phase, the agent makes a sequence of decisions while interacting with the data-generating process and observing feedback in the form of costs. The agent aims to discover the best possible actions by interacting with the environment and consistently updating their actions based on their experience, while often, also taking random actions to assist in exploring the state space - the classic exploration-exploitation trade-off (Sutton and Barto, 2018). In RL, uncertainty in the data-generating process can have substantial effects on performance. Indeed, the environmental randomness may result in algorithms optimized for "on-average" performance to have large variance across scenarios.

With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems. Despite its reputation, data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning hard to be practical in a wide range of areas. Plenty of methods have been developed for sample efficient deep reinforcement learning, such as environment modeling, experience transfer, and distributed modifications, amongst which, distributed deep reinforcement learning has shown its potential in various applications, such as human-computer gaming, and intelligent transportation. In this paper, we conclude the state of this exciting field, by comparing the classical distributed deep reinforcement learning methods, and studying important components to achieve efficient distributed learning, covering single player single agent distributed deep reinforcement learning to the most complex multiple players multiple agents distributed deep reinforcement learning. Furthermore, we review recently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distributed versions. By analyzing their strengths and weaknesses, a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released, which is further validated on Wargame, a complex environment, showing usability of the proposed toolbox for multiple players and multiple agents distributed deep reinforcement learning under complex games. Finally, we try to point out challenges and future trends, hoping this brief review can provide a guide or a spark for researchers who are interested in distributed deep reinforcement learning.

Reinforcement Learning (RL) algorithms have been successfully applied to real world situations like illegal smuggling, poaching, deforestation, climate change, airport security, etc. These scenarios can be framed as Stackelberg security games (SSGs) where defenders and attackers compete to control target resources. The algorithm's competency is assessed by which agent is controlling the targets. This review investigates modeling of SSGs in RL with a focus on possible improvements of target representations in RL algorithms.

In the past few years, Deep Reinforcement Learning (DRL) has become a valuable solution to automatically learn efficient resource management strategies in complex networks. In many scenarios, the learning task is performed in the Cloud, while experience samples are generated directly by edge nodes or users. Therefore, the learning task involves some data exchange which, in turn, subtracts a certain amount of transmission resources from the system. This creates a friction between the need to speed up convergence towards an effective strategy, which requires the allocation of resources to transmit learning samples, and the need to maximize the amount of resources used for data plane communication, maximizing users' Quality of Service (QoS), which requires the learning process to be efficient, i.e., minimize its overhead. In this paper, we investigate this trade-off and propose a dynamic balancing strategy between the learning and data planes, which allows the centralized learning agent to quickly converge to an efficient resource allocation strategy while minimizing the impact on QoS. Simulation results show that the proposed method outperforms static allocation methods, converging to the optimal policy (i.e., maximum efficacy and minimum overhead of the learning plane) in the long run.

Efficient data transfers over high-speed, long-distance shared networks require proper utilization of available network bandwidth. Using parallel TCP streams enables an application to utilize network parallelism and can improve transfer throughput; however, finding the optimum number of parallel TCP streams is challenging due to nondeterministic background traffic sharing the same network. Additionally, the non-stationary, multi-objectiveness, and partially-observable nature of network signals in the host systems add extra complexity in finding the current network condition. In this work, we present a novel approach to finding the optimum number of parallel TCP streams using deep reinforcement learning (RL). We devise a learning-based algorithm capable of generalizing different network conditions and utilizing the available network bandwidth intelligently. Contrary to rule-based heuristics that do not generalize well in unknown network scenarios, our RL-based solution can dynamically discover and adapt the parallel TCP stream numbers to maximize the network bandwidth utilization without congesting the network and ensure fairness among contending transfers. We extensively evaluated our RL-based algorithm's performance, comparing it with several state-of-the-art online optimization algorithms. The results show that our RL-based algorithm can find near-optimal solutions 40% faster while achieving up to 15% higher throughput. We also show that, unlike a greedy algorithm, our devised RL-based algorithm can avoid network congestion and fairly share the available network resources among contending transfers.

As one of the most striking advances in online advertising, real-time bidding (RTB) [3] has received increasing attention since it improves the efficiency and transparency of the ad ecosystem [4]. In RTB, the publishing media sells ad impressions through public auctions, and advertisers bid on their targeting ad impressions in real-time and pay for their winning impressions. Therefore, it requires the bidding agent to make accurate user feedback predictions for each ad impression and determine a reasonable bidding price to maximize the long-term revenue [5] of the ad campaign. Figure 1 illustrates the entire process of an advertiser participating in bidding for an ad impression. Initially, the advertiser registers an ad campaign on the Demand Side Platform (DSP) and specifies the campaign's budget as well as targeting rules for each ad delivery period (usually a day). Bidding agents running on DSP participate in RTB on behalf of advertisers.

Advancements in reinforcement learning (RL) have inspired new directions in intelligent automation of network defense. However, many of these advancements have either outpaced their application to network security or have not considered the challenges associated with implementing them in the real-world. To understand these problems, this work evaluates several RL approaches implemented in the second edition of the CAGE Challenge, a public competition to build an autonomous network defender agent in a high-fidelity network simulator. Our approaches all build on the Proximal Policy Optimization (PPO) family of algorithms, and include hierarchical RL, action masking, custom training, and ensemble RL. We find that the ensemble RL technique performs strongest, outperforming our other models and taking second place in the competition. To understand applicability to real environments we evaluate each method's ability to generalize to unseen networks and against an unknown attack strategy. In unseen environments, all of our approaches perform worse, with degradation varied based on the type of environmental change. Against an unknown attacker strategy, we found that our models had reduced overall performance even though the new strategy was less efficient than the ones our models trained on.

Curiosity for machine agents has been a focus of lively research activity. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that have not yet been well-explored in machine intelligence. In this work, we conduct a comprehensive, multidisciplinary survey of the field of animal and machine curiosity. As a principal contribution of this work, we use this survey as a foundation to introduce and define what we consider to be five of the most important properties of specific curiosity: 1) directedness towards inostensible referents, 2) cessation when satisfied, 3) voluntary exposure, 4) transience, and 5) coherent long-term learning. As a second main contribution of this work, we show how these properties may be implemented together in a proof-of-concept reinforcement learning agent: we demonstrate how the properties manifest in the behaviour of this agent in a simple non-episodic grid-world environment that includes curiosity-inducing locations and induced targets of curiosity. As we would hope, our example of a computational specific curiosity agent exhibits short-term directed behaviour while updating long-term preferences to adaptively seek out curiosity-inducing situations. This work, therefore, presents a landmark synthesis and translation of specific curiosity to the domain of machine learning and reinforcement learning and provides a novel view into how specific curiosity operates and in the future might be integrated into the behaviour of goal-seeking, decision-making computational agents in complex environments.

Training self-driving cars is often challenging since they require a vast amount of labeled data in multiple real-world contexts, which is computationally and memory intensive. Researchers often resort to driving simulators to train the agent and transfer the knowledge to a real-world setting. Since simulators lack realistic behavior, these methods are quite inefficient. To address this issue, we introduce a framework (perception, planning, and control) in a real-world driving environment that transfers the real-world environments into gaming environments by setting up a reliable Markov Decision Process (MDP). We propose variations of existing Reinforcement Learning (RL) algorithms in a multi-agent setting to learn and execute the discrete control in real-world environments. Experiments show that the multi-agent setting outperforms the single-agent setting in all the scenarios. We also propose reliable initialization, data augmentation, and training techniques that enable the agents to learn and generalize to navigate in a real-world environment with minimal input video data, and with minimal training. Additionally, to show the efficacy of our proposed algorithm, we deploy our method in the virtual driving environment TORCS.