Variance minimization for continuous-time Markov decision processes: two approaches

This paper studies the limit average variance criterion for continuous-time Markov decision processes in Polish spaces. Based on two approaches, this paper proves not only the existence of solutions to the variance minimization optimality equation and the existence of a variance minimal policy that is canonical, but also the existence of solutions to the two variance minimization optimality inequalities and the existence of a variance minimal policy which may not be canonical. An example is given to illustrate all of our conditions.

Robust analysis of discounted Markov decision processes with uncertain transition probabilities

Optimal policies in Markov decision problems may be quite sensitive with regard to transition probabilities.In practice,some transition probabilities may be uncertain.The goals of the present study are to find the robust range for a certain optimal policy and to obtain value intervals of exact transition probabilities.Our research yields powerful contributions for Markov decision processes(MDPs)with uncertain transition probabilities.We first propose a method for estimating unknown transition probabilities based on maximum likelihood.Since the estimation may be far from accurate,and the highest expected total reward of the MDP may be sensitive to these transition probabilities,we analyze the robustness of an optimal policy and propose an approach for robust analysis.After giving the definition of a robust optimal policy with uncertain transition probabilities represented as sets of numbers,we formulate a model to obtain the optimal policy.Finally,we define the value intervals of the exact transition probabilities and construct models to determine the lower and upper bounds.Numerical examples are given to show the practicability of our methods.

Seeking for Passenger under Dynamic Prices: A Markov Decision Process Approach

In recent years, ride-on-demand (RoD) services such as Uber and Didi are becoming increasingly popular. Different from traditional taxi services, RoD services adopt dynamic pricing mechanisms to manipulate the supply and demand on the road, and such mechanisms improve service capacity and quality. Seeking route recommendation has been widely studied in taxi service. In RoD services, the dynamic price is a new and accurate indicator that represents the supply and demand condition, but it is yet rarely studied in providing clues for drivers to seek for passengers. In this paper, we proposed to incorporate the impacts of dynamic prices as a key factor in recommending seeking routes to drivers. We first showed the importance and need to do that by analyzing real service data. We then designed a Markov Decision Process (MDP) model based on passenger order and car GPS trajectories datasets, and took into account dynamic prices in designing rewards. Results show that our model not only guides drivers to locations with higher prices, but also significantly improves driver revenue. Compared with things with the drivers before using the model, the maximum yield after using it can be increased to 28%.

A dynamical neural network approach for distributionally robust chance-constrained Markov decision process

In this paper,we study the distributionally robust joint chance-constrained Markov decision process.Utilizing the logarithmic transformation technique,we derive its deterministic reformulation with bi-convex terms under the moment-based uncertainty set.To cope with the non-convexity and improve the robustness of the solution,we propose a dynamical neural network approach to solve the reformulated optimization problem.Numerical results on a machine replacement problem demonstrate the efficiency of the proposed dynamical neural network approach when compared with the sequential convex approximation approach.

Heterogeneous Network Selection Optimization Algorithm Based on a Markov Decision Model

A network selection optimization algorithm based on the Markov decision process(MDP)is proposed so that mobile terminals can always connect to the best wireless network in a heterogeneous network environment.Considering the different types of service requirements,the MDP model and its reward function are constructed based on the quality of service(QoS)attribute parameters of the mobile users,and the network attribute weights are calculated by using the analytic hierarchy process(AHP).The network handoff decision condition is designed according to the different types of user services and the time-varying characteristics of the network,and the MDP model is solved by using the genetic algorithm and simulated annealing(GA-SA),thus,users can seamlessly switch to the network with the best long-term expected reward value.Simulation results show that the proposed algorithm has good convergence performance,and can guarantee that users with different service types will obtain satisfactory expected total reward values and have low numbers of network handoffs.

Recorded recurrent deep reinforcement learning guidance laws for intercepting endoatmospheric maneuvering missiles

This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.

Performance sensitivities for parameterized Markov systems

It is known that the performance potentials (or equivalentiy, perturbation realization factors) can be used as building blocks for performance sensitivities of Markov systems. In parameterized systems, the changes in parameters may only affect some states, and the explicit transition probability matrix may not be known. In this paper, we use an example to show that we can use potentials to construct performance sensitivities in a more flexible way; only the potentials at the affected states need to be estimated, and the transition probability matrix need not be known. Policy iteration algorithms, which are simpler than the standard one, can be established.

Grid Integration of Wind Generation Considering Remote Wind Farms:Hybrid Markovian and Interval Unit Commitment

Grid integration of wind power is essential to reduce fossil fuel usage but challenging in view of the intermittent nature of wind.Recently,we developed a hybrid Markovian and interval approach for the unit commitment and economic dispatch problem where power generation of conventional units is linked to local wind states to dampen the effects of wind uncertainties.Also,to reduce complexity,extreme and expected states are considered as interval modeling.Although this approach is effective,the fact that major wind farms are often located in remote locations and not accompanied by conventional units leads to conservative results.Furthermore,weights of extreme and expected states in the objective function are difficult to tune,resulting in significant differences between optimization and simulation costs.In this paper,each remote wind farm is paired with a conventional unit to dampen the effects of wind uncertainties without using expensive utility-scaled battery storage,and extra constraints are innovatively established to model pairing.Additionally,proper weights are derived through a novel quadratic fit of cost functions.The problem is solved by using a creative integration of our recent surrogate Lagrangian relaxation and branch-and-cut.Results demonstrate modeling accuracy,computational efficiency,and significant reduction of conservativeness of the previous approach.

Opportunistic admission and resource allocation for slicing enhanced IoT networks

Network slicing is envisioned as one of the key techniques to meet the extremely diversified service requirements of the Internet of Things(IoT)as it provides an enhanced user experience and elastic resource configuration.In the context of slicing enhanced IoT networks,both the Service Provider(SP)and Infrastructure Provider(InP)face challenges of ensuring efficient slice construction and high profit in dynamic environments.These challenges arise from randomly generated and departed slice requests from end-users,uncertain resource availability,and multidimensional resource allocation.Admission and resource allocation for distinct demands of slice requests are the key issues in addressing these challenges and should be handled effectively in dynamic environments.To this end,we propose an Opportunistic Admission and Resource allocation(OAR)policy to deal with the issues of random slicing requests,uncertain resource availability,and heterogeneous multi-resources.The key idea of OAR is to allow the SP to decide whether to accept slice requests immediately or defer them according to the load and price of resources.To cope with the random slice requests and uncertain resource availability,we formulated this issue as a Markov Decision Process(MDP)to obtain the optimal admission policy,with the aim of maximizing the system reward.Furthermore,the buyer-seller game theory approach was adopted to realize the optimal resource allocation,while motivating each SP and InP to maximize their rewards.Our numerical results show that the proposed OAR policy can make reasonable decisions effectively and steadily,and outperforms the baseline schemes in terms of the system reward.

SBFT:A BFT Consensus Mechanism Based on DQN Algorithm for Industrial Internet of Thing

With the development and widespread use of blockchain in recent years,many projects have introduced blockchain technology to solve the growing security issues of the Industrial Internet of Things(IIoT).However,due to the conflict between the operational performance and security of the blockchain system and the compatibility issues with a large number of IIoT devices running together,the mainstream blockchain system cannot be applied to IIoT scenarios.In order to solve these problems,this paper proposes SBFT(Speculative Byzantine Consensus Protocol),a flexible and scalable blockchain consensus mechanism for the Industrial Internet of Things.SBFT has a consensus process based on speculation,improving the throughput and consensus speed of blockchain systems and reducing communication overhead.In order to improve the compatibility and scalability of the blockchain system,we select some nodes to participate in the consensus,and these nodes have better performance in the network.Since multiple properties determine node performance,we abstract the node selection problem as a joint optimization problem and use Dueling Deep Q Learning(DQL)to solve it.Finally,we evaluate the performance of the scheme through simulation,and the simulation results prove the superiority of our scheme.

Multi-Agent Deep Reinforcement Learning for Cross-Layer Scheduling in Mobile Ad-Hoc Networks

Due to the fading characteristics of wireless channels and the burstiness of data traffic,how to deal with congestion in Ad-hoc networks with effective algorithms is still open and challenging.In this paper,we focus on enabling congestion control to minimize network transmission delays through flexible power control.To effectively solve the congestion problem,we propose a distributed cross-layer scheduling algorithm,which is empowered by graph-based multi-agent deep reinforcement learning.The transmit power is adaptively adjusted in real-time by our algorithm based only on local information(i.e.,channel state information and queue length)and local communication(i.e.,information exchanged with neighbors).Moreover,the training complexity of the algorithm is low due to the regional cooperation based on the graph attention network.In the evaluation,we show that our algorithm can reduce the transmission delay of data flow under severe signal interference and drastically changing channel states,and demonstrate the adaptability and stability in different topologies.The method is general and can be extended to various types of topologies.

Optimal Policies for Quantum Markov Decision Processes

Markov decision process(MDP)offers a general framework for modelling sequential decision making where outcomes are random.In particular,it serves as a mathematical framework for reinforcement learning.This paper introduces an extension of MDP,namely quantum MDP(q MDP),that can serve as a mathematical model of decision making about quantum systems.We develop dynamic programming algorithms for policy evaluation and finding optimal policies for q MDPs in the case of finite-horizon.The results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.

Convergence of Markov decision processes with constraints and state-action dependent discount factors

This paper is concerned with the convergence of a sequence of discrete-time Markov decision processes(DTMDPs)with constraints,state-action dependent discount factors,and possibly unbounded costs.Using the convex analytic approach under mild conditions,we prove that the optimal values and optimal policies of the original DTMDPs converge to those of the"limit"one.Furthermore,we show that any countablestate DTMDP can be approximated by a sequence of finite-state DTMDPs,which are constructed using the truncation technique.Finally,we illustrate the approximation by solving a controlled queueing system numerically,and give the corresponding error bound of the approximation.

First passage Markov decision processes with constraints and varying discount factors

This paper focuses on the constrained optimality problem （COP） of first passage discrete-time Markov decision processes （DTMDPs） in denumerable state and compact Borel action spaces with multi-constraints, state-dependent discount factors, and possibly unbounded costs. By means of the properties of a so-called occupation measure of a policy, we show that the constrained optimality problem is equivalent to an （infinite-dimensional） linear programming on the set of occupation measures with some constraints, and thus prove the existence of an optimal policy under suitable conditions. Furthermore, using the equivalence between the constrained optimality problem and the linear programming, we obtain an exact form of an optimal policy for the case of finite states and actions. Finally, as an example, a controlled queueing system is given to illustrate our results.

A review on Markov Decision Processes

MARKOV decision processes (MDPs) have been studied by mathematicians, probabilists, operation researchers and engineers since the late 1950s. In an MDPs a stochastic, dynamic system is controlled by a 'policy' selected by a decision-maker/controller, with the goal of maximizing an overall reward function that is an appropriately defined aggregate of immediate rewards, over either finite or infinite time horizon.As such MDPs are a useful paradigm for modeling many processes occurring naturally in the management and engineering contexts..

Solving Markov Decision Processes with Downside Risk Adjustment

Markov decision processes （MDPs） and their variants are widely studied in the theory of controls for stochastic discrete- event systems driven by Markov chains. Much of the literature focusses on the risk-neutral criterion in which the expected rewards, either average or discounted, are maximized. There exists some literature on MDPs that takes risks into account. Much of this addresses the exponential utility （EU） function and mechanisms to penalize different forms of variance of the rewards. EU functions have some numerical deficiencies, while variance measures variability both above and below the mean rewards; the variability above mean rewards is usually beneficial and should not be penalized/avoided. As such, risk metrics that account for pre-specified targets （thresholds） for rewards have been considered in the literature, where the goal is to penalize the risks of revenues falling below those targets. Existing work on MDPs that takes targets into account seeks to minimize risks of this nature. Minimizing risks can lead to poor solutions where the risk is zero or near zero, but the average rewards are also rather low. In this paper, hence, we study a risk-averse criterion, in particular the so-called downside risk, which equals the probability of the revenues falling below a given target, where, in contrast to minimizing such risks, we only reduce this risk at the cost of slightly lowered average rewards. A solution where the risk is low and the average reward is quite high, although not at its maximum attainable value, is very attractive in practice. To be more specific, in our formulation, the objective function is the expected value of the rewards minus a scalar times the downside risk. In this setting, we analyze the infinite horizon MDP, the finite horizon MDP, and the infinite horizon semi-MDP （SMDP）. We develop dynamic programming and reinforcement learning algorithms for the finite and infinite horizon. The algorithms are tested in numerical studies and show encouraging performance.

SINGULARLY PERTURBED MARKOV DECISION PROCESSES WITH INCLUSION OF TRANSIENT STATES

This paper is concerned with the continuous-time Markov decision processes (MDP) having weak and strong interactions. Using a hierarchical approach, the state space of the underlying Markov chain can be decomposed into several groups of recurrent states and a group of transient states resulting in a singularly perturbed MDP formulation. Instead of solving the original problem directly, a limit problem that is much simpler to handle is derived. On the basis of the optical solution of the limit problem, nearly optimal decisions are constructed for the original problem. The asymptotic optimality of the constructed control is obtained; the rate of convergence is ascertained.

First Passage Risk Probability Minimization for Piecewise Deterministic Markov Decision Processes

This paper is an attempt to study the minimization problem of the risk probability of piecewise deterministic Markov decision processes(PDMDPs)with unbounded transition rates and Borel spaces.Different from the expected discounted and average criteria in the existing literature,we consider the risk probability that the total rewards produced by a system do not exceed a prescribed goal during a first passage time to some target set,and aim to find a policy that minimizes the risk probability over the class of all history-dependent policies.Under suitable conditions,we derive the optimality equation(OE)for the probability criterion,prove that the value function of the minimization problem is the unique solution to the OE,and establish the existence ofε(≥0)-optimal policies.Finally,we provide two examples to illustrate our results.

A Comparison of PPO, TD3 and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation

Deep reinforcement learning (deep RL) has the potential to replace classic robotic controllers. State-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient and Soft Actor-Critic Reinforcement Algorithms, to mention a few, have been investigated for training robots to walk. However, conflicting performance results of these algorithms have been reported in the literature. In this work, we present the performance analysis of the above three state-of-the-art Deep Reinforcement algorithms for a constant velocity walking task on a quadruped. The performance is analyzed by simulating the walking task of a quadruped equipped with a range of sensors present on a physical quadruped robot. Simulations of the three algorithms across a range of sensor inputs and with domain randomization are performed. The strengths and weaknesses of each algorithm for the given task are discussed. We also identify a set of sensors that contribute to the best performance of each Deep Reinforcement algorithm.

Analysis of a POMDP Model for an Optimal Maintenance Problem with Multiple Imperfect Repairs

I consider a system whose deterioration follows a discrete-time and discrete-state Markov chain with an absorbing state. When the system is put into practice, I may select operation (wait), imperfect repair, or replacement at each discrete-time point. The true state of the system is not known when it is operated. Instead, the system is monitored after operation and some incomplete information concerned with the deterioration is obtained for decision making. Since there are multiple imperfect repairs, I can select one option from them when the imperfect repair is preferable to operation and replacement. To express this situation, I propose a POMDP model and theoretically investigate the structure of an optimal maintenance policy minimizing a total expected discounted cost for an unbounded horizon. Then two stochastic orders are used for the analysis of our problem.