When blockchain meets AI: Optimal mining strategy achieved by machine learning

This chapter theoretically and experimentally analyzes the consensus algorithms in blockchains. Consensus is one of the key problems in blockchains, and there are several candidate consensus algorithms for public and consortium/private blockchains with different security and performance levels.The first part of this chapter analyzes the proof‐of‐work (PoW) consensus algorithm. In PoW‐based public blockchains, miners can conduct different mining strategies to selfishly increase their own revenues. Previously, the most profitable mining strategy was believed to be honest mining encoded in the default blockchain protocol. It was shown later that it is possible to gain more mining rewards by deviating from honest mining and conducting some malicious mining strategies. In particular, the mining problem can be formulated as a Markov decision process (MDP), which can be solved to give the optimal mining strategy. However, solving the mining MDP requires knowing the values of various parameters that characterize the blockchain network model. In real blockchain networks, these parameter values are not easy to obtain and may change over time. This hinders the use of the MDP model‐based solution. In the first part of this chapter, we employ RL to dynamically learn a mining strategy with performance approaching that of the optimal mining strategy. Since the mining MDP problem has a nonlinear objective function (rather than linear functions of standard MDP problems), we design a new multi‐dimensional RL algorithm to solve the problem. Experimental results indicate that, without knowing the parameter values of the mining MDP model, our multi‐dimensional RL mining algorithm can still achieve optimal performance over time‐varying blockchain networks.The second part of this chapter analyzes the Raft consensus algorithm that is usually adopted in the consortium/private blockchains. There are many articles analyzing the performance of threat models for blockchains. However, the issue of network stability has not received much attention, which in fact affects the blockchain performance. This part studies the performance of Raft in networks with non‐negligible packet loss rate. In particular, we propose a simple but accurate analytical model to analyze the distributed network split probability. At a given time, we explicitly present the network split probability as a function of the network size, the packet loss rate, and the election timeout period. To validate our analysis, we implement a Raft simulator and the simulation results coincide with the analytical results. With the proposed model, one can predict the network split time and probability in theory and optimize the parameters in Raft consensus algorithm.

Recently, studies on early-exit mechanisms have emerged to reduce the computational cost during the inference process of deep learning models. However, most existing early-exit architectures simply determine early exiting based only on a target confidence level in the prediction, without any consideration of the computational cost. Such an early-exit criterion fails to balance accuracy and cost, making it difficult to use in various environments. To address this problem, we propose a novel, cost-effective early-exit architecture in which an early-exit criterion is designed based on the Markov decision process (MDP). Since the early-exit decisions within an early-exit model are sequential, we model them as an MDP problem to maximize accuracy as much as possible while minimizing the computational cost. Then, we develop a cost-effective early-exit algorithm using reinforcement learning that solves the MDP problem. For each input sample, the algorithm dynamically makes early-exit decisions considering the relative importance of accuracy and computational cost in a given environment, thereby balancing the trade-off between accuracy and cost regardless of the environment. Consequently, it can be used in various environments, even in a resource-constrained environment. Through extensive experiments, we demonstrate that our proposed architecture can effectively balance the trade-off in different environments, while the existing architectures fail to do so since they focus only on reducing their cost while preventing the degradation of accuracy.

Introduction Reinforcement learning formalizes the concept of learning from interactions.1 Broadly, reinforcement learning focuses on a setting in which an agent (decision maker) sequentially interacts with an environment that is partially unknown to them. At each stage, the agent takes an action and receives a reward. The objective of the agent is to maximize rewards accumulated in the long run. There are many situations in health care where decisions are made sequentially for which reinforcement learning approaches could prove useful for decision making. Throughout this article, we consider treatment prescription as an archetypical example to connect reinforcement learning concepts to a health care setting. In this setting, the care provider, the prescribed treatment, and the patients can be viewed as the agent, the action, and the environment, respectively, as depicted in Figure 1.Figure 1: Sequential treatment of AKI or CKD complications modeled as a reinforcement learning problem.Background In this section, with the objective of making reinforcement learning literature more accessible to a clinical audience, we briefly introduce related fundamental concepts and approaches. We refer the interested reader to Sutton and Barto1 for a comprehensive introduction to reinforcement learning. Markov Decision Processes Markov decision processes (MDPs) are a formalism of the sequential decision-making problem that has been central to the theoretical and practical advancements of reinforcement learning. In each stage of an MDP, the agent observes the state of the environment and takes an action, which, in turn, results in a change of the state. This change of state is assumed to be probabilistic with the next state being determined only by the preceding state, the chosen action, and the transition probability. The agent also receives a reward that is a function of the taken action, the preceding state, and the subsequent state. In an MDP, the objective of the agent is to maximize the return defined as the reward accumulated over a time horizon. In some applications, it is common to consider the horizon to be infinite, in which case the future rewards are discounted by a factor smaller than one. The selection of action by the agent on the basis of the observed state is known as the policy. More formally, a policy is a probabilistic mapping from states to each possible action. Because the policy and the reward are a function of the state, it is critical to estimate the utility of being in a certain state. More specifically, the value function is defined as the expected return starting from a given state under the chosen policy. Under this formalism, the objective of the agent is to find the optimal policy that maximizes the value function for all states. Reinforcement Learning Methods Action-value methods are a class of reinforcement learning methods in which the actions are chosen on the basis of the estimation of their long-term value. A prominent example of an action-value method is Q-learning in which the agent iteratively takes actions with the highest estimated values and updates the action-state value function on the basis of new observations. Policy gradient methods are another class of reinforcement learning methods that seek to optimize the policy directly instead of choosing actions on the basis of their respective estimated value. Such methods could be advantageous in health care applications that entail a large number of possible actions, e.g., when recommending a wide range of drug dosages or treatment options. Clinical Applications Reinforcement learning frameworks and methods are broadly applicable to clinical settings in which decisions are made sequentially. A prominent clinical application of reinforcement learning is for treatment recommendation, which has been studied across a variety of diseases and treatments including radiation and chemotherapy for cancer, brain stimulation for epilepsy, and treatment strategies for sepsis.2–5 In such treatment recommendation settings, a policy is commonly known as a dynamic treatment regime. There are various other clinical applications of reinforcement learning including diagnosis, medical imaging, and decision support tools (see refs. 2–5 and the references therein). Reinforcement Learning in Nephrology Although there have been recent applications of machine learning in nephrology,6,7 to the best of the authors' knowledge, the application of reinforcement learning to nephrology has been primarily limited to optimizing the erythropoietin dosage in hemodialysis patients.8,9 However, there are other settings where reinforcement learning has the potential to improve patient care in nephrology. For example, reinforcement learning methods can be adopted in the treatment of the complications of AKI or CKD (Figure 1). In this problem, the state models the conditions of the patient (e.g., vital signs, laboratory test results including urine and blood tests, and urine output measurements). The action refers to the treatment options (e.g., the dosage of medications such as sodium polystyrene sulfonate, and hemodialysis). The reward models the improvement in patient conditions. Similarly, reinforcement learning can help automate and optimize the dosage of immunosuppressive drugs in kidney transplants. Challenges and Opportunities Despite the success of reinforcement learning in several simplified clinical settings, their large-scale application to patient care faces several open challenges. The complexity of human biology complicates modeling clinical decision making as a reinforcement learning problem. The state space in such settings is often enormous, which could make a purely computational approach infeasible. Moreover, modeling all potential objectives a priori as a reward function may not be feasible. To overcome these challenges and realize the potential of reinforcement learning, clinical insight can play a pivotal role. More specifically, restricting the state space to only include highly relevant clinical variables could greatly reduce the computational complexity. Furthermore, using inverse reinforcement learning,2 relevant reward functions can be learned from retrospective studies assuming the optimality of clinical decisions. Another critical challenge is addressing moral and ethical concerns. It is imperative to ensure that reinforcement learning methods do not cause harm to the patient. To this end, there exists a need for a thorough validation of such methods before their use in patient care. Hence, there is a need to go beyond retrospective studies that have been used for the proof of concept of most existing reinforcement learning methods in health care applications.2,3 The lessons learned from the success of reinforcement learning in other application areas (e.g., self-driving cars) can help navigate the path to realizing its potential in health care. Accessible open-source simulation environments that enable researchers to compare various approaches are essential to the field of reinforcement learning. OpenAI Gym is currently the leading toolkit containing a wide range of simulated environments, e.g., surgical robotics.10 The development of high-quality and reliable simulation environments for nephrology and other health care applications can facilitate the development and validation of reinforcement learning methods beyond limited retrospective studies. The adoption of methods validated in such simulation environments in actual clinical settings will require clinicians' oversight. Similar to how self-driving cars require a human driver to ensure collision avoidance, clinicians' oversight is critical to ensure the safety of the patients, especially in the early stages of the adoption of reinforcement learning methods. The data from clinicians' decisions (e.g., overruling the automated treatment recommendation) can be used to improve the reliability of autonomous systems over time and reduce the burden of clinicians' oversight.

With the deep integration of advanced information technologies such as artificial intelligence and traditional energy technologies, smart energy systems have been proposed as a method to provide the best solution for the coordination, balance, and control of the entire energy system. As a new way of energy balance and interaction in the user side energy market, peer-to-peer (P2P) electricity transaction can effectively promote energy sharing within the user group and improve the economic benefits of users participating in the energy market. Reinforcement learning (RL) is an artificial intelligence method in which agents continuously acquire relevant experience and knowledge during the interaction with the environment, automatically update their decision-making behavior, and achieve maximum return. It is suitable for P2P transaction decision analysis of small-scale users in the context of smart energy. Firstly, this paper establishes a P2P transaction model that includes a participant model, equipment model and price model. Secondly, the transaction problem is equivalent to a Markov decision process (MDP) and each learning element model is established. Then, the MDP problem is solved and analyzed using SARSA RL algorithm with average discrete processing. Finally, a case study of a community with multiple users is conducted to verify the effectiveness, economy, and security of RL method in solving energy storage action selection and transaction decision problems of energy storage users.

In this paper we present an algorithm, the Goal Agnostic Planner (GAP), which combines elements of Reinforcement Learning (RL) and Markov Decision Processes (MDPs) into an elegant, effective system for learning to solve sequential problems. The GAP algorithm does not require the design of either an explicit world model or a reward function to drive policy determination, and is capable of operating on both MDP and RL domain problems. The construction of the GAP lends itself to several analytic guarantees such as policy optimality, exponential goal achievement rates, reciprocal learning rates, measurable robustness to error, and explicit convergence conditions for abstracted states. Empirical results confirm these predictions, demonstrate effectiveness over a wide range of domains, and show that the GAP algorithm performance is an order of magnitude faster than standard reinforcement learning and produces plans of equal quality to MDPs, without requiring design of reward functions.

Reinforcement Learning (RL) is a machine learning methodology that develops the capability to make sequential decisions in intricate issues using trial-and-error techniques. RL has become increasingly prevalent for decision-making and control tasks in diverse fields such as industrial processes, biochemical systems and energy management. This review paper presents a comprehensive examination of the development, models, algorithms and practical uses of RL, with a specific emphasis on its application in process control. The study examines the fundamental theories, methodology and applications of RL, classifying them into two categories: classical RL such as such as Markov decision processes (MDP) and deep RL viz., actor critic methods. RL is a topic of discussion in multiple process industries, such as industrial chemical process control, biochemical process control, energy systems, wastewater treatment and the oil and gas sector. Nevertheless, the paper also highlights challenges that hinder its larger acceptance, including the requirement for substantial computational resources, the complexity of simulating real-world settings and the challenge of guaranteeing the stability and resilience of RL algorithms in dynamic and unpredictable environments. RL has demonstrated significant promise, but more research is needed to fully integrate it into industrial and environmental systems in order to solve the current challenges. Abbreviations: AC: Actor critic; AI: Artificial intelligence; ANN: Artificial neural networks; A3C: Asynchronous advantage actor critic; CRL : Classical Reinforcement learning; CV : Controlled variable; DDPG : Deep deterministic policy gradient; DQN: Deep Q network; DRL: Deep reinforcement learning; DP: Dynamic programming; FOMDP: Fully observable Markov decision process; GRU: Gated recurrent unit; LQR: Linear quadratic regulator; LSTM: Long short-term memory; ML: Machine learning; MV : Manipulated variable; MC: Monte Carlo; MDP: Markov decision process; MPC: Model predictive controller; MIMO: Multi input multi output; PG: Policy gradient; PID: Proportional integral derivative; PPO: Proximal policy optimisation; RL: Reinforcement learning; PPO: Proximal policy optimisation; SAC: Soft actor critic; SISO: Single input single output; TD: Temporal difference; TRPO: Trust region policy optimisation; TD3: Twin delayed deep deterministic policy gradient.

In computer science, reinforcement learning is a powerful framework with which artificial agents can learn to maximize their performance for any given Markov decision process (MDP). Advances over the last decade, in combination with deep neural networks, have enjoyed performance advantages over humans in many difficult task settings. However, such frameworks perform far less favorably when evaluated in their ability to generalize or transfer representations across different tasks. Existing algorithms that facilitate transfer typically are limited to cases in which the transition function or the optimal policy is portable to new contexts, but achieving “deep transfer” characteristic of human behavior has been elusive. Such transfer typically requires discovery of abstractions that permit analogical reuse of previously learned representations to superficially distinct tasks. Here, we demonstrate that abstractions that minimize error in predictions of reward outcomes generalize across tasks with different transition and reward functions. Such reward-predictive representations compress the state space of a task into a lower dimensional representation by combining states that are equivalent in terms of both the transition and reward functions. Because only state equivalences are considered, the resulting state representation is not tied to the transition and reward functions themselves and thus generalizes across tasks with different reward and transition functions. These results contrast with those using abstractions that myopically maximize reward in any given MDP and motivate further experiments in humans and animals to investigate if neural and cognitive systems involved in state representation perform abstractions that facilitate such equivalence relations.

Reinforcement Learning (RL) Markov Decision Processes is studied with an emphasis on the well-studied exploration problem. We first formulate and discuss a definition of “efficient” algorithms that is termed Probably Approximately Correct (PAC) in RL. Next we provide general sufficient conditions for such an algorithm that applies to several different modeling assumptions. The conditions can be used to demonstrate that efficient learning is possible in finite MDPs, with either a model-based or model-free approach, in factored MDPs, and in continuous MDPs with linear dynamics. In the reinforcement-learning (RL) problem (Sutton & Barto 1998), an agent acts in an unknown or incompletely known environment with the goal of maximizing an external reward signal. In the most standard mathematical formulation of the problem, the environment is modeled as a Markov Decision Process (MDP) and the goal of the agent is to obtain near-optimal discounted return. Over the years, many algorithms have been proposed for this problem, but analyses of their performances have been relatively scarce. In fact, until recently, most theoretical guarantees have been that certain algorithms will discover an optimal policy in the limit, after an infinite amount of experience. In contrast, several attempts have been made to study “Probably Approximately Correct” or PAC-MDP algorithms, which exhibit near-optimal behavior in polynomial time and experience. This paper discusses several extensions of those results. We present a theorem that provides sufficient conditions for an algorithm to be PAC-MDP. We examine these conditions and show how they can be applied to prove that efficient learning is possible in three interesting scenerios: finite MDPs (i.e. the “Tabular case”),

We study state aggregation for Markov decision processes (MDPs) with long-run average-cost optimality criterion in this paper. The aggregation is based on a definition of an (/spl epsiv//sub p/, /spl epsiv//sub f/)-lumpable partition of the state space, where the difference between the control effect of any control action on any two states belonging to the same subset in the partition is bounded by /spl epsiv//sub p/ for the state-transition effect and /spl epsiv//sub f/ for the cost effect. The states in the same partition subset are treated into one meta-state to obtain an aggregated Markov chain. We then construct an aggregated MDP with average cost on the aggregated Markov chain. We develop an algorithm to find the solution to this aggregated MDP problem and show its performance is within some o(/spl epsiv//sub p/, /spl epsiv//sub f/) neighborhood of the optimal solution to the original MDP problem. In real applications, the (/spl epsiv//sub p/, /spl epsiv//sub f/)-lumpable partition is usually obtained empirically. However, we also study the problem of looking for the coarsest (/spl epsiv//sub p/, /spl epsiv//sub f/)-lumpable partition, i.e., the partition with minimum number of subsets, given /spl epsiv//sub p/ and /spl epsiv//sub f/. We prove that this partitioning problem is in the time complexity class of P-hard, which is not easier than the original MDP problem in the class of P-complete.

With the sharing economy boom, there is a notable increase in the number of car-sharing corporations, which provided a variety of travel options and improved convenience and functionality. Owing to the similarity in the travel patterns of the urban population, car-sharing system often faces the problem of imbalance in the number of shared cars within the spatial distribution, especially during the rush hours. There are many challenges in redressing this imbalance, such as insufficient data and the large state space. In this study, we propose a new reward method called Double P (Picking & Parking) Bonus (DPB). We model the research problem as a Markov Decision Process (MDP) problem and introduce Deep Deterministic Policy Gradient, a state-of-the-art reinforcement learning framework, to find a solution. The results show that the rewarding mechanism embodied in the DPB method can indeed guide the users’ behaviors through price leverage, increase user stickiness, and cultivate user habits, thereby boosting the service provider’s long-term profit. In addition, taking the battery power of the shared car into consideration, we use the method of hierarchical reinforcement learning for station scheduling. This station scheduling method encourages the user to place the car that needs to be charged on the charging post within a certain site. It can ensure the effective use of charging pile resources, thereby rendering the efficient functioning of shared cars.

Distribution network reconfiguration (DNR) is a technique that changes the status of sectionalizing and tie switches for various purposes such as loss minimization, voltage profile improvement, load leveling, and hosting capacity increase. Although previous algorithms for DNR show good performance, they still have practical limitations. Most of the algorithms assumed that a central coordinator knows all parameters and/or perfect states in a distribution network. Reinforcement learning which is a model-free optimization technique can be a key way to overcome these limitations. This work proposes a DNR scheme using deep reinforcement learning to minimize power loss defined by the amount of line loss and renewable energy curtailment. We model the DNR problem as a Markov decision process (MDP) problem and apply the reinforcement learning algorithm to solve this problem in real-time. Simulation result using 33-bus radial distribution system shows that the proposed scheme shows similar performance compared to an existing method which uses all information on the distribution network.

This chapter presents an overview of simulation-based techniques useful for solving Markov decision processes (MDPs). MDPs model problems of sequential decision-making under uncertainty, in which decisions made in each state collectively affect the trajectory of the states visited by the system over a time horizon of interest. Traditionally, MDPs have been solved via dynamic programming (DP), which requires the transition probability model that is difficult to derive in many realistic settings. The use of simulation for solving MDPs allows us to bypass the transition probability model and solve large-scale MDPs considered intractable to solve by traditional DP. The simulation-based methodology for solving MDPs, which like DP is also rooted in the Bellman equations, goes by names such as reinforcement learning, neuro-DP, and approximate or adaptive DP. We begin with a description of algorithms for infinite-horizon discounted reward MDPs, followed by the same for infinite-horizon average reward MDPs. Then we present a discussion on finite-horizon MDPs. For each problem considered, we present a step-by-step description of a selected group of algorithms. In making this selection, we have attempted to blend the old and the classical with more recent developments. Finally, after touching upon extensions and convergence theory, we conclude with a brief summary of some applications and directions for future research.

Ant-TD: Ant colony optimization plus temporal difference reinforcement learning for multi-label feature selection

Pulse jamming is one of the common malicious jamming patterns that can significantly reduce the of wireless communication's reliability. This paper investigates the problem of anti-jamming communication in a random pulse jamming environment. In order to obtain the countermeasure in time domain, the Markov decision process (MDP) is employed to model and analyze the above problem, and a time-domain anti-pulse jamming algorithm (TDAA) based on reinforcement learning is proposed. The proposed algorithm learns from the dynamic interaction with the jamming environment to gradually approximate the optimal time-domain strategy. The optimal strategy enables the transmitter to switch between two states, i.e. “active” and “silent”, to avoid random pulse jamming. In addition, a state estimation and adjustment method for the random pulse jamming environment is introduced to improve the robustness of the proposed TDAA. Simulation results show that, compared with continuous transmission, the proposed TDAA can effectively reduce the jamming collision ratio and significantly improve the normalized throughput. And compared with transmitting terminal Q-learning algorithm (TTQA), the proposed TDAA has higher time utilization ratio and normalized throughput.

Advanced planning for autonomous vehicles using reinforcement learning and deep inverse reinforcement learning