Process mining is a methodology for the derivation and analysis of process models based on the event log. When process mining is employed to analyze business processes, the process discovery step, the conformance checking step, and the enhancements step are repeated. If a user wants to analyze a process from multiple perspectives (such as activity perspectives, originator perspectives, and time perspectives), the above procedure, inconveniently, has to be repeated over and over again. Although past studies involving process mining have applied detailed stepwise methodologies, no attempt has been made to incorporate and optimize multi-perspective process mining procedures. This paper contributes to developing a solution approach to this problem. First, we propose an automatic discovery framework of a multi-perspective process model based on deep Q-Learning. Our Dual Experience Replay with Experience Distribution (DERED) approach can automatically perform process model discovery steps, conformance check steps, and enhancements steps. Second, we propose a new method that further optimizes the experience replay (ER) method, one of the key algorithms of deep Q-learning, to improve the learning performance of reinforcement learning agents. Finally, we validate our approach using six real-world event datasets collected in port logistics, steel manufacturing, finance, IT, and government administration. We show that our DERED approach can provide users with multi-perspective, high-quality process models that can be employed more conveniently for multi-perspective process mining.
Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every iteration when multiple agents update their policies at the same time. Starting from first principle, in this paper, we manage to solve the non-stationarity problem by proposing bidirectional action-dependent Q-learning (ACE). Central to the development of ACE is the sequential decision-making process wherein only one agent is allowed to take action at one time. Within this process, each agent maximizes its value function given the actions taken by the preceding agents at the inference stage. In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action. Given the design of bidirectional dependency, ACE effectively turns a multiagent MDP into a single-agent MDP. We implement the ACE framework by identifying the proper network representation to formulate the action dependency, so that the sequential decision process is computed implicitly in one forward pass. To validate ACE, we compare it with strong baselines on two MARL benchmarks. Empirical experiments demonstrate that ACE outperforms the state-of-the-art algorithms on Google Research Football and StarCraft Multi-Agent Challenge by a large margin. In particular, on SMAC tasks, ACE achieves 100% success rate on almost all the hard and super-hard maps. We further study extensive research problems regarding ACE, including extension, generalization, and practicability. Code is made available to facilitate further research.
The potential of offline reinforcement learning (RL) is that high-capacity models trained on large, heterogeneous datasets can lead to agents that generalize broadly, analogously to similar advances in vision and NLP. However, recent works argue that offline RL methods encounter unique challenges to scaling up model capacity. Drawing on the learnings from these works, we re-examine previous design choices and find that with appropriate choices: ResNets, cross-entropy based distributional backups, and feature normalization, offline Q-learning algorithms exhibit strong performance that scales with model capacity. Using multi-task Atari as a testbed for scaling and generalization, we train a single policy on 40 games with near-human performance using up-to 80 million parameter networks, finding that model performance scales favorably with capacity. In contrast to prior work, we extrapolate beyond dataset performance even when trained entirely on a large (400M transitions) but highly suboptimal dataset (51% human-level performance). Compared to return-conditioned supervised approaches, offline Q-learning scales similarly with model capacity and has better performance, especially when the dataset is suboptimal. Finally, we show that offline Q-learning with a diverse dataset is sufficient to learn powerful representations that facilitate rapid transfer to novel games and fast online learning on new variations of a training game, improving over existing state-of-the-art representation learning approaches.
Automated Market Makers (AMMs) have cemented themselves as an integral part of the decentralized finance (DeFi) space. AMMs are a type of exchange that allows users to trade assets without the need for a centralized exchange. They form the foundation for numerous decentralized exchanges (DEXs), which help facilitate the quick and efficient exchange of on-chain tokens. All present-day popular DEXs are static protocols, with fixed parameters controlling the fee and the curvature - they suffer from invariance and cannot adapt to quickly changing market conditions. This characteristic may cause traders to stay away during high slippage conditions brought about by intractable market movements. We propose an RL framework to optimize the fees collected on an AMM protocol. In particular, we develop a Q-Learning Agent for Market Making Protocols (QLAMMP) that learns the optimal fee rates and leverage coefficients for a given AMM protocol and maximizes the expected fee collected under a range of different market conditions. We show that QLAMMP is consistently able to outperform its static counterparts under all the simulated test conditions.
Recent technological advancements in space, air, and ground components have made possible a new network paradigm called space-air-ground integrated network (SAGIN). Unmanned aerial vehicles (UAVs) play a key role in SAGINs. However, due to UAVs' high dynamics and complexity, real-world deployment of a SAGIN becomes a significant barrier to realizing such SAGINs. UAVs are expected to meet key performance requirements with limited maneuverability and resources with space and terrestrial components. Therefore, employing UAVs in various usage scenarios requires well-designed planning in algorithmic approaches. This paper provides an essential review and analysis of recent learning algorithms in a UAV-assisted SAGIN. We consider possible reward functions and discuss the state-of-the-art algorithms for optimizing the reward functions, including Q-learning, deep Q-learning, multi-armed bandit, particle swarm optimization, and satisfaction-based learning algorithms. Unlike other survey papers, we focus on the methodological perspective of the optimization problem, applicable to various missions on a SAGIN. We consider real-world configurations and the 2-dimensional (2D) and 3-dimensional (3D) UAV trajectories to reflect deployment cases. Our simulations suggest the 3D satisfaction-based learning algorithm outperforms other approaches in most cases. With open challenges discussed at the end, we aim to provide design and deployment guidelines for UAV-assisted SAGINs.
Deep reinforcement learning (DRL) requires the collection of interventional data, which is sometimes expensive and even unethical in the real world, such as in the autonomous driving and the medical field. Offline reinforcement learning promises to alleviate this issue by exploiting the vast amount of observational data available in the real world. However, observational data may mislead the learning agent to undesirable outcomes if the behavior policy that generates the data depends on unobserved random variables (i.e., confounders). In this paper, we propose two deconfounding methods in DRL to address this problem. The methods first calculate the importance degree of different samples based on the causal inference technique, and then adjust the impact of different samples on the loss function by reweighting or resampling the offline dataset to ensure its unbiasedness. These deconfounding methods can be flexibly combined with existing model-free DRL algorithms such as soft actor-critic and deep Q-learning, provided that a weak condition can be satisfied by the loss functions of these algorithms. We prove the effectiveness of our deconfounding methods and validate them experimentally.
Multi-agent systems in which secondary agents with conflicting agendas also alter their methods need opponent modeling. In this study, we simulate the main agent's and secondary agents' tactics using Double Deep Q-Networks (DDQN) with a prioritized experience replay mechanism. Then, under the opponent modeling setup, a Mixture-of-Experts architecture is used to identify various opponent strategy patterns. Finally, we analyze our models in two environments with several agents. The findings indicate that the Mixture-of-Experts model, which is based on opponent modeling, performs better than DDQN.
Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider policy divergence as behavior regularization, ignoring the effect of how the offline state distribution differs with that of the learning policy, which may lead to under-pessimism for some states and over-pessimism for others. Taking account of this problem, we propose a principled algorithmic framework for offline RL, called \emph{State-Aware Proximal Pessimism} (SA-PP). The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way. We first provide theoretical justifications on the superiority of SA-PP over previous algorithms, demonstrating that SA-PP produces a lower suboptimality upper bound in a broad range of settings. Furthermore, we propose a new algorithm named \emph{State-Aware Conservative Q-Learning} (SA-CQL), by building SA-PP upon representative CQL algorithm with the help of DualDICE for estimating discounted stationary state distribution ratios. Extensive experiments on standard offline RL benchmark show that SA-CQL outperforms the popular baselines on a large portion of benchmarks and attains the highest average return.
Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article presents a novel deep reinforcement learning (DRL) controller to aid conflict resolution for autonomous free flight. Although DRL has achieved important advancements in this field, the existing works pay little attention to the explainability and safety issues related to DRL controllers, particularly the safety under adversarial attacks. To address those two issues, we design a fully explainable DRL framework wherein we: 1) decompose the coupled Q value learning model into a safety-awareness and efficiency (reach the target) one; and 2) use information from surrounding intruders as inputs, eliminating the needs of central controllers. In our simulated experiments, we show that by decoupling the safety-awareness and efficiency, we can exceed performance on free flight control tasks while dramatically improving explainability on practical. In addition, the safety Q learning module provides rich information about the safety situation of environments. To study the safety under adversarial attacks, we additionally propose an adversarial attack strategy that can impose both safety-oriented and efficiency-oriented attacks. The adversarial aims to minimize safety/efficiency by only attacking the agent at a few time steps. In the experiments, our attack strategy increases as many collisions as the uniform attack (i.e., attacking at every time step) by only attacking the agent four times less often, which provide insights into the capabilities and restrictions of the DRL in future ATC designs. The source code is publicly available at https://github.com/WLeiiiii/Gym-ATC-Attack-Project.
Cognitive Radio (CR) is a paradigm shift in wireless communications to resolve the spectrum scarcity issue with the ability to self-organize, self-plan and self-regulate. On the other hand, wireless devices that can learn from their environment can also be taught things by malicious elements of their environment, and hence, malicious attacks are a great concern in the CR, especially for physical layer security. This thesis introduces a data-driven Self-Awareness (SA) module in CR that can support the system to establish secure networks against various attacks from malicious users. Such users can manipulate the radio spectrum to make the CR learn wrong behaviours and take mistaken actions. The SA module consists of several functionalities that allow the radio to learn a hierarchical representation of the environment and grow its long-term memory incrementally. Therefore, this novel SA module is a way forward towards realizing the original vision of CR (i.e. Mitola's Radio) and AI-enabled radios. Experimental results show that introducing the novel SA functionalities provides the high accuracy of characterizing, detecting, classifying and predicting the jammer's activities and outperforms conventional detection methods such as Energy detectors and advanced classification methods such as Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Stacked Autoencoder (SAE). It also verifies that the proposed approach achieves a higher degree of explainability than deep learning techniques and verifies the capability to learn an efficient strategy to avoid future attacks with higher convergence speed compared to conventional Frequency Hopping and Q-learning.
Learning directed acyclic graph (DAG) that describes the causality of observed data is a very challenging but important task. Due to the limited quantity and quality of observed data, and non-identifiability of causal graph, it is almost impossible to infer a single precise DAG. Some methods approximate the posterior distribution of DAGs to explore the DAG space via Markov chain Monte Carlo (MCMC), but the DAG space is over the nature of super-exponential growth, accurately characterizing the whole distribution over DAGs is very intractable. In this paper, we propose {Reinforcement Causal Structure Learning on Order Graph} (RCL-OG) that uses order graph instead of MCMC to model different DAG topological orderings and to reduce the problem size. RCL-OG first defines reinforcement learning with a new reward mechanism to approximate the posterior distribution of orderings in an efficacy way, and uses deep Q-learning to update and transfer rewards between nodes. Next, it obtains the probability transition model of nodes on order graph, and computes the posterior probability of different orderings. In this way, we can sample on this model to obtain the ordering with high probability. Experiments on synthetic and benchmark datasets show that RCL-OG provides accurate posterior probability approximation and achieves better results than competitive causal discovery algorithms.
This effort is focused on examining the behavior of reinforcement learning systems in personalization environments and detailing the differences in policy entropy associated with the type of learning algorithm utilized. We demonstrate that Policy Optimization agents often possess low-entropy policies during training, which in practice results in agents prioritizing certain actions and avoiding others. Conversely, we also show that Q-Learning agents are far less susceptible to such behavior and generally maintain high-entropy policies throughout training, which is often preferable in real-world applications. We provide a wide range of numerical experiments as well as theoretical justification to show that these differences in entropy are due to the type of learning being employed.
This paper introduces the deployment of unmanned aerial vehicles (UAVs) as lightweight wireless access points that leverage the fixed infrastructure in the context of the emerging open radio access network (O-RAN). More precisely, we propose an aerial radio unit that dynamically serves an under served area and connects to the distributed unit via a wireless fronthaul between the UAV and the closest tower. In this paper we analyze the UAV trajectory in terms of artificial intelligence (AI) when it serves both UEs and central units (CUs) at the same time in multi input multi output (MIMO) fading channel. We first demonstrate the nonconvexity of the problem of maximizing the overall network throughput based on UAV location, and then we use two different machine learning approaches to solve it. We first assume that the environment is a gridworld and then let the UAV explore the environment by flying from point A to point B, using both the offline Q-learning and the online SARSA algorithm and the achieved path-loss as the reward. With the intention of maximizing the average payoff, the trajectory in the second scenario is described as a Markov decision process (MDP). According to simulations, MDP produces better results in a smaller setting and in less time. In contrast, SARSA performs better in larger environments at the expense of a longer flight duration.
In reinforcement learning, the performance of learning agents is highly sensitive to the choice of time discretization. Agents acting at high frequencies have the best control opportunities, along with some drawbacks, such as possible inefficient exploration and vanishing of the action advantages. The repetition of the actions, i.e., action persistence, comes into help, as it allows the agent to visit wider regions of the state space and improve the estimation of the action effects. In this work, we derive a novel All-Persistence Bellman Operator, which allows an effective use of both the low-persistence experience, by decomposition into sub-transition, and the high-persistence experience, thanks to the introduction of a suitable bootstrap procedure. In this way, we employ transitions collected at any time scale to update simultaneously the action values of the considered persistence set. We prove the contraction property of the All-Persistence Bellman Operator and, based on it, we extend classic Q-learning and DQN. After providing a study on the effects of persistence, we experimentally evaluate our approach in both tabular contexts and more challenging frameworks, including some Atari games.
Traditional multi-agent reinforcement learning (MARL) algorithms, such as independent Q-learning, struggle when presented with partially observable scenarios, and where agents are required to develop delicate action sequences. This is often the result of the reward for a good action only being available after other agents have taken theirs, and these actions are not credited accordingly. Recurrent neural networks have proven to be a viable solution strategy for solving these types of problems, resulting in significant performance increase when compared to other methods. In this paper, we explore a different approach and focus on the experiences used to update the action-value functions of each agent. We introduce the concept of credit-cognisant rewards (CCRs), which allows an agent to perceive the effect its actions had on the environment as well as on its co-agents. We show that by manipulating these experiences and constructing the reward contained within them to include the rewards received by all the agents within the same action sequence, we are able to improve significantly on the performance of independent deep Q-learning as well as deep recurrent Q-learning. We evaluate and test the performance of CCRs when applied to deep reinforcement learning techniques at the hands of a simplified version of the popular card game Hanabi.
Object packing by autonomous robots is an im-portant challenge in warehouses and logistics industry. Most conventional data-driven packing planning approaches focus on regular cuboid packing, which are usually heuristic and limit the practical use in realistic applications with everyday objects. In this paper, we propose a deep hierarchical reinforcement learning approach to simultaneously plan packing sequence and placement for irregular object packing. Specifically, the top manager network infers packing sequence from six principal view heightmaps of all objects, and then the bottom worker network receives heightmaps of the next object to predict the placement position and orientation. The two networks are trained hierarchically in a self-supervised Q-Learning framework, where the rewards are provided by the packing results based on the top height , object volume and placement stability in the box. The framework repeats sequence and placement planning iteratively until all objects have been packed into the box or no space is remained for unpacked items. We compare our approach with existing robotic packing methods for irregular objects in a physics simulator. Experiments show that our approach can pack more objects with less time cost than the state-of-the-art packing methods of irregular objects. We also implement our packing plan with a robotic manipulator to show the generalization ability in the real world.
Process optimization for metal additive manufacturing (AM) is crucial to ensure repeatability, control microstructure, and minimize defects. Despite efforts to address this via the traditional design of experiments and statistical process mapping, there is limited insight on an on-the-fly optimization framework that can be integrated into a metal AM system. Additionally, most of these methods, being data-intensive, cannot be supported by a metal AM alloy or system due to budget restrictions. To tackle this issue, the article introduces a Reinforcement Learning (RL) methodology transformed into an optimization problem in the realm of metal AM. An off-policy RL framework based on Q-learning is proposed to find optimal laser power ($P$) - scan velocity ($v$) combinations with the objective of maintaining steady-state melt pool depth. For this, an experimentally validated Eagar-Tsai formulation is used to emulate the Laser-Directed Energy Deposition environment, where the laser operates as the agent across the $P-v$ space such that it maximizes rewards for a melt pool depth closer to the optimum. The culmination of the training process yields a Q-table where the state ($P,v$) with the highest Q-value corresponds to the optimized process parameter. The resultant melt pool depths and the mapping of Q-values to the $P-v$ space show congruence with experimental observations. The framework, therefore, provides a model-free approach to learning without any prior.
Multi-objective reinforcement learning (MORL) is a relatively new field which builds on conventional Reinforcement Learning (RL) to solve multi-objective problems. One of common algorithm is to extend scalar value Q-learning by using vector Q values in combination with a utility function, which captures the user's preference for action selection. This study follows on prior works, and focuses on what factors influence the frequency with which value-based MORL Q-learning algorithms learn the optimal policy for an environment with stochastic state transitions in scenarios where the goal is to maximise the Scalarised Expected Return (SER) - that is, to maximise the average outcome over multiple runs rather than the outcome within each individual episode. The analysis of the interaction between stochastic environment and MORL Q-learning algorithms run on a simple Multi-objective Markov decision process (MOMDP) Space Traders problem with different variant versions. The empirical evaluations show that well designed reward signal can improve the performance of the original baseline algorithm, however it is still not enough to address more general environment. A variant of MORL Q-Learning incorporating global statistics is shown to outperform the baseline method in original Space Traders problem, but remains below 100 percent effectiveness in finding the find desired SER-optimal policy at the end of training. On the other hand, Option learning is guarantied to converge to desired SER-optimal policy but it is not able to scale up to solve more complex problem in real-life. The main contribution of this thesis is to identify the extent to which the issue of noisy Q-value estimates impacts on the ability to learn optimal policies under the combination of stochastic environments, non-linear utility and a constant learning rate.
Deep Q-learning based algorithms have been applied successfully in many decision making problems, while their theoretical foundations are not as well understood. In this paper, we study a Fitted Q-Iteration with two-layer ReLU neural network parameterization, and find the sample complexity guarantees for the algorithm. Our approach estimates the Q-function in each iteration using a convex optimization problem. We show that this approach achieves a sample complexity of $\tilde{\mathcal{O}}(1/\epsilon^{2})$, which is order-optimal. This result holds for a countable state-spaces and does not require any assumptions such as a linear or low rank structure on the MDP.
We study optimal control in models with latent factors where the agent controls the distribution over actions, rather than actions themselves, in both discrete and continuous time. To encourage exploration of the state space, we reward exploration with Tsallis Entropy and derive the optimal distribution over states - which we prove is $q$-Gaussian distributed with location characterized through the solution of an FBS$\Delta$E and FBSDE in discrete and continuous time, respectively. We discuss the relation between the solutions of the optimal exploration problems and the standard dynamic optimal control solution. Finally, we develop the optimal policy in a model-agnostic setting along the lines of soft $Q$-learning. The approach may be applied in, e.g., developing more robust statistical arbitrage trading strategies.